Tag Archives: Three

#436578 AI Just Discovered a New Antibiotic to ...

Penicillin, one of the greatest discoveries in the history of medicine, was a product of chance.

After returning from summer vacation in September 1928, bacteriologist Alexander Fleming found a colony of bacteria he’d left in his London lab had sprouted a fungus. Curiously, wherever the bacteria contacted the fungus, their cell walls broke down and they died. Fleming guessed the fungus was secreting something lethal to the bacteria—and the rest is history.

Fleming’s discovery of penicillin and its later isolation, synthesis, and scaling in the 1940s released a flood of antibiotic discoveries in the next few decades. Bacteria and fungi had been waging an ancient war against each other, and the weapons they’d evolved over eons turned out to be humanity’s best defense against bacterial infection and disease.

In recent decades, however, the flood of new antibiotics has slowed to a trickle.

Their development is uneconomical for drug companies, and the low-hanging fruit has long been picked. We’re now facing the emergence of strains of super bacteria resistant to one or more antibiotics and an aging arsenal to fight them with. Gone unchallenged, an estimated 700,000 deaths worldwide due to drug resistance could rise to as many as 10 million in 2050.

Increasingly, scientists warn the tide is turning, and we need a new strategy to keep pace with the remarkably quick and boundlessly creative tactics of bacterial evolution.

But where the golden age of antibiotics was sparked by serendipity, human intelligence, and natural molecular weapons, its sequel may lean on the uncanny eye of artificial intelligence to screen millions of compounds—and even design new ones—in search of the next penicillin.

Hal Discovers a Powerful Antibiotic
In a paper published this week in the journal, Cell, MIT researchers took a step in this direction. The team says their machine learning algorithm discovered a powerful new antibiotic.

Named for the AI in 2001: A Space Odyssey, the antibiotic, halicin, successfully wiped out dozens of bacterial strains, including some of the most dangerous drug-resistant bacteria on the World Health Organization’s most wanted list. The bacteria also failed to develop resistance to E. coli during a month of observation, in stark contrast to existing antibiotic ciprofloxacin.

“In terms of antibiotic discovery, this is absolutely a first,” Regina Barzilay, a senior author on the study and computer science professor at MIT, told The Guardian.

The algorithm that discovered halicin was trained on the molecular features of 2,500 compounds. Nearly half were FDA-approved drugs, and another 800 naturally occurring. The researchers specifically tuned the algorithm to look for molecules with antibiotic properties but whose structures would differ from existing antibiotics (as halicin’s does). Using another machine learning program, they screened the results for those likely to be safe for humans.

Early study suggests halicin attacks the bacteria’s cell membranes, disrupting their ability to produce energy. Protecting the cell membrane from halicin might take more than one or two genetic mutations, which could account for its impressive ability to prevent resistance.

“I think this is one of the more powerful antibiotics that has been discovered to date,” James Collins, an MIT professor of bioengineering and senior author told The Guardian. “It has remarkable activity against a broad range of antibiotic-resistant pathogens.”

Beyond tests in petri-dish bacterial colonies, the team also tested halicin in mice. The antibiotic cleared up infections of a strain of bacteria resistant to all known antibiotics in a day. The team plans further study in partnership with a pharmaceutical company or nonprofit, and they hope to eventually prove it safe and effective for use in humans.

This last bit remains the trickiest step, given the cost of getting a new drug approved. But Collins hopes algorithms like theirs will help. “We could dramatically reduce the cost required to get through clinical trials,” he told the Financial Times.

A Universe of Drugs Awaits
The bigger story may be what happens next.

How many novel antibiotics await discovery, and how far can AI screening take us? The initial 6,000 compounds scanned by Barzilay and Collins’s team is a drop in the bucket.

They’ve already begun digging deeper by setting the algorithm loose on 100 million molecules from an online library of 1.5 billion compounds called the ZINC15 database. This first search took three days and turned up 23 more candidates that, like halicin, differ structurally from existing antibiotics and may be safe for humans. Two of these—which the team will study further—appear to be especially powerful.

Even more ambitiously, Barzilay hopes the approach can find or even design novel antibiotics that kill bad bacteria with alacrity while sparing the good guys. In this way, a round of antibiotics would cure whatever ails you without taking out your whole gut microbiome in the process.

All this is part of a larger movement to use machine learning algorithms in the long, expensive process of drug discovery. Other players in the area are also training AI on the vast possibility space of drug-like compounds. Last fall, one of the leaders in the area, Insilico, was challenged by a partner to see just how fast their method could do the job. The company turned out a new a proof-of-concept drug candidate in only 46 days.

The field is still developing, however, and it has yet to be seen exactly how valuable these approaches will be in practice. Barzilay is optimistic though.

“There is still a question of whether machine-learning tools are really doing something intelligent in healthcare, and how we can develop them to be workhorses in the pharmaceuticals industry,” she said. “This shows how far you can adapt this tool.”

Image Credit: Halicin (top row) prevented the development of antibiotic resistance in E. coli, while ciprofloxacin (bottom row) did not. Collins Lab at MIT Continue reading

Posted in Human Robots

#436559 This Is What an AI Said When Asked to ...

“What’s past is prologue.” So says the famed quote from Shakespeare’s The Tempest, alleging that we can look to what has already happened as an indication of what will happen next.

This idea could be interpreted as being rather bleak; are we doomed to repeat the errors of the past until we correct them? We certainly do need to learn and re-learn life lessons—whether in our work, relationships, finances, health, or other areas—in order to grow as people.

Zooming out, the same phenomenon exists on a much bigger scale—that of our collective human history. We like to think we’re improving as a species, but haven’t yet come close to doing away with the conflicts and injustices that plagued our ancestors.

Zooming back in (and lightening up) a little, what about the short-term future? What might happen over the course of this year, and what information would we use to make educated guesses about it?

The editorial team at The Economist took a unique approach to answering these questions. On top of their own projections for 2020, including possible scenarios in politics, economics, and the continued development of technologies like artificial intelligence, they looked to an AI to make predictions of its own. What it came up with is intriguing, and a little bit uncanny.

[For the full list of the questions and answers, read The Economist article].

An AI That Reads—Then Writes
Almost exactly a year ago, non-profit OpenAI announced it had built a neural network for natural language processing called GPT-2. The announcement was met with some controversy, as it included the caveat that the tool would not be immediately released to the public due to its potential for misuse. It was then released in phases over the course of several months.

GPT-2’s creators upped the bar on quality when training the neural net; rather than haphazardly feeding it low-quality text, they only used articles that got more than three upvotes on Reddit (admittedly, this doesn’t guarantee high quality across the board—but it’s something).

The training dataset consisted of 40GB of text. For context, 1GB of text is about 900,000 ASCII pages or 130,000 double-spaced Microsoft Word pages.

The tool has no understanding of the text it’s generating, of course. It uses language patterns and word sequences to draw statistical associations between words and phrases, building a sort of guidebook for itself (not unlike the grammar rules and vocabulary words you might study when trying to learn a foreign language). It then uses that guidebook to answer questions or predict what will come after a particular sequence of words.

GPT-2’s creators did note that when the model is trained on specifically-selected datasets for narrower applications, its replies become more convincing.

Some Light Editing
Though the Economist article detailing GPT-2’s predictions describes the text the model generated as “unedited,” this isn’t wholly accurate. In a Medium post, deputy editor Tom Standage describes the methodology he used, and it does involve a degree of tweaking.

Standage wrote an introductory paragraph, followed by his opening question (“Greetings, GPT-2. Have you done an interview before?”). He configured the tool to generate five responses to each subsequent question then selected the best answer, deleting any questions GPT-2 came up with as part of its response.

AI’s View of the World—and Itself
The questions Standage asked ranged from tech-related (the future of AI, technological unemployment, misuse of technology) to political and economic (re-election of Donald Trump, the US-China trade war). Here are a couple of his questions and GPT-2’s answers:

Q: Do fake news stories, generated using AI, pose a threat to democracy? Are we likely to see this tactic being used in the 2020 American presidential elections?
A: Yes, we’ll probably see them. It’s just a matter of when. Fake news stories are generally generated by political campaigns, and have the potential to have a huge impact on the outcome of an election. This is because they spread misinformation, often with no basis in fact.

Q: How do you see the economic outlook for 2020?
A: I think it is very unclear. The outlook for the UK economy is uncertain, but the American economy is very strong. I think we are going to have a lot of turbulence in the world economy.

While some of its answers seemed insightful—when asked about the future of AI, GPT-2 advised that we treat the technology like a tool and “put as much effort into developing [it] as necessary, rather than worrying that it’s going to harm us and destroy our lives”—many of the responses were quite vague. One answer, for example, mentions that there will “probably be major changes in China.” Are we talking political changes? Social? Economic? All of the above?

However, while nothing the AI wrote was particularly illuminating or new, it’s impressive that it was able to expound on the correct topic for each question, and in fully coherent English.

GPT-2 named itself—AI—as the most important disruptive technology to watch in 2020. This is telling; it’s coming from a synthesis of millions of pages of published articles. If GPT-2 thinks AI is more important than, say, gene editing or quantum computing, it could be right. Or it could simply be that AI is at peak hype, and as such more is being written about it than about other technologies.

Equally intriguing was GPT-2’s response when asked whether Donald Trump will win a second term: “I think he will not win a second term. I think he will be defeated in the general election.” Some deeper insight there would be great, but hey—we’ll take it.

Predicting Predictions
Since an AI can read and synthesize vast data sets much faster than we can, it’s being used to predict all kinds of things, from virus outbreaks to crime. But asking it to philosophize on the future based on the (Reddit-curated) past is new, and if you think about it, a pretty fascinating undertaking.

As GPT-2 and tools like it continually improve, we’ll likely see them making more—and better—predictions of the future. In the meantime, let’s hope that the new data these models are trained on—news of what’s happening this week, this month, this year—add to an already-present sense of optimism.

When asked if it had any advice for readers, GPT-2 replied, “The big projects that you think are impossible today are actually possible in the near future.”

Image Credit: Alexas_Fotos from Pixabay Continue reading

Posted in Human Robots

#436504 20 Technology Metatrends That Will ...

In the decade ahead, waves of exponential technological advancements are stacking atop one another, eclipsing decades of breakthroughs in scale and impact.

Emerging from these waves are 20 “metatrends” likely to revolutionize entire industries (old and new), redefine tomorrow’s generation of businesses and contemporary challenges, and transform our livelihoods from the bottom up.

Among these metatrends are augmented human longevity, the surging smart economy, AI-human collaboration, urbanized cellular agriculture, and high-bandwidth brain-computer interfaces, just to name a few.

It is here that master entrepreneurs and their teams must see beyond the immediate implications of a given technology, capturing second-order, Google-sized business opportunities on the horizon.

Welcome to a new decade of runaway technological booms, historic watershed moments, and extraordinary abundance.

Let’s dive in.

20 Metatrends for the 2020s
(1) Continued increase in global abundance: The number of individuals in extreme poverty continues to drop, as the middle-income population continues to rise. This metatrend is driven by the convergence of high-bandwidth and low-cost communication, ubiquitous AI on the cloud, and growing access to AI-aided education and AI-driven healthcare. Everyday goods and services (finance, insurance, education, and entertainment) are being digitized and becoming fully demonetized, available to the rising billion on mobile devices.

(2) Global gigabit connectivity will connect everyone and everything, everywhere, at ultra-low cost: The deployment of both licensed and unlicensed 5G, plus the launch of a multitude of global satellite networks (OneWeb, Starlink, etc.), allow for ubiquitous, low-cost communications for everyone, everywhere, not to mention the connection of trillions of devices. And today’s skyrocketing connectivity is bringing online an additional three billion individuals, driving tens of trillions of dollars into the global economy. This metatrend is driven by the convergence of low-cost space launches, hardware advancements, 5G networks, artificial intelligence, materials science, and surging computing power.

(3) The average human healthspan will increase by 10+ years: A dozen game-changing biotech and pharmaceutical solutions (currently in Phase 1, 2, or 3 clinical trials) will reach consumers this decade, adding an additional decade to the human healthspan. Technologies include stem cell supply restoration, wnt pathway manipulation, senolytic medicines, a new generation of endo-vaccines, GDF-11, and supplementation of NMD/NAD+, among several others. And as machine learning continues to mature, AI is set to unleash countless new drug candidates, ready for clinical trials. This metatrend is driven by the convergence of genome sequencing, CRISPR technologies, AI, quantum computing, and cellular medicine.

(4) An age of capital abundance will see increasing access to capital everywhere: From 2016 – 2018 (and likely in 2019), humanity hit all-time highs in the global flow of seed capital, venture capital, and sovereign wealth fund investments. While this trend will witness some ups and downs in the wake of future recessions, it is expected to continue its overall upward trajectory. Capital abundance leads to the funding and testing of ‘crazy’ entrepreneurial ideas, which in turn accelerate innovation. Already, $300 billion in crowdfunding is anticipated by 2025, democratizing capital access for entrepreneurs worldwide. This metatrend is driven by the convergence of global connectivity, dematerialization, demonetization, and democratization.

(5) Augmented reality and the spatial web will achieve ubiquitous deployment: The combination of augmented reality (yielding Web 3.0, or the spatial web) and 5G networks (offering 100Mb/s – 10Gb/s connection speeds) will transform how we live our everyday lives, impacting every industry from retail and advertising to education and entertainment. Consumers will play, learn, and shop throughout the day in a newly intelligent, virtually overlaid world. This metatrend will be driven by the convergence of hardware advancements, 5G networks, artificial intelligence, materials science, and surging computing power.

(6) Everything is smart, embedded with intelligence: The price of specialized machine learning chips is dropping rapidly with a rise in global demand. Combined with the explosion of low-cost microscopic sensors and the deployment of high-bandwidth networks, we’re heading into a decade wherein every device becomes intelligent. Your child’s toy remembers her face and name. Your kids’ drone safely and diligently follows and videos all the children at the birthday party. Appliances respond to voice commands and anticipate your needs.

(7) AI will achieve human-level intelligence: As predicted by technologist and futurist Ray Kurzweil, artificial intelligence will reach human-level performance this decade (by 2030). Through the 2020s, AI algorithms and machine learning tools will be increasingly made open source, available on the cloud, allowing any individual with an internet connection to supplement their cognitive ability, augment their problem-solving capacity, and build new ventures at a fraction of the current cost. This metatrend will be driven by the convergence of global high-bandwidth connectivity, neural networks, and cloud computing. Every industry, spanning industrial design, healthcare, education, and entertainment, will be impacted.

(8) AI-human collaboration will skyrocket across all professions: The rise of “AI as a Service” (AIaaS) platforms will enable humans to partner with AI in every aspect of their work, at every level, in every industry. AIs will become entrenched in everyday business operations, serving as cognitive collaborators to employees—supporting creative tasks, generating new ideas, and tackling previously unattainable innovations. In some fields, partnership with AI will even become a requirement. For example: in the future, making certain diagnoses without the consultation of AI may be deemed malpractice.

(9) Most individuals adapt a JARVIS-like “software shell” to improve their quality of life: As services like Alexa, Google Home, and Apple Homepod expand in functionality, such services will eventually travel beyond the home and become your cognitive prosthetic 24/7. Imagine a secure JARVIS-like software shell that you give permission to listen to all your conversations, read your email, monitor your blood chemistry, etc. With access to such data, these AI-enabled software shells will learn your preferences, anticipate your needs and behavior, shop for you, monitor your health, and help you problem-solve in support of your mid- and long-term goals.

(10) Globally abundant, cheap renewable energy: Continued advancements in solar, wind, geothermal, hydroelectric, nuclear, and localized grids will drive humanity towards cheap, abundant, and ubiquitous renewable energy. The price per kilowatt-hour will drop below one cent per kilowatt-hour for renewables, just as storage drops below a mere three cents per kilowatt-hour, resulting in the majority displacement of fossil fuels globally. And as the world’s poorest countries are also the world’s sunniest, the democratization of both new and traditional storage technologies will grant energy abundance to those already bathed in sunlight.

(11) The insurance industry transforms from “recovery after risk” to “prevention of risk”: Today, fire insurance pays you after your house burns down; life insurance pays your next-of-kin after you die; and health insurance (which is really sick insurance) pays only after you get sick. This next decade, a new generation of insurance providers will leverage the convergence of machine learning, ubiquitous sensors, low-cost genome sequencing, and robotics to detect risk, prevent disaster, and guarantee safety before any costs are incurred.

(12) Autonomous vehicles and flying cars will redefine human travel (soon to be far faster and cheaper): Fully autonomous vehicles, car-as-a-service fleets, and aerial ride-sharing (flying cars) will be fully operational in most major metropolitan cities in the coming decade. The cost of transportation will plummet 3-4X, transforming real estate, finance, insurance, the materials economy, and urban planning. Where you live and work, and how you spend your time, will all be fundamentally reshaped by this future of human travel. Your kids and elderly parents will never drive. This metatrend will be driven by the convergence of machine learning, sensors, materials science, battery storage improvements, and ubiquitous gigabit connections.

(13) On-demand production and on-demand delivery will birth an “instant economy of things”: Urban dwellers will learn to expect “instant fulfillment” of their retail orders as drone and robotic last-mile delivery services carry products from local supply depots directly to your doorstep. Further riding the deployment of regional on-demand digital manufacturing (3D printing farms), individualized products can be obtained within hours, anywhere, anytime. This metatrend is driven by the convergence of networks, 3D printing, robotics, and artificial intelligence.

(14) Ability to sense and know anything, anytime, anywhere: We’re rapidly approaching the era wherein 100 billion sensors (the Internet of Everything) is monitoring and sensing (imaging, listening, measuring) every facet of our environments, all the time. Global imaging satellites, drones, autonomous car LIDARs, and forward-looking augmented reality (AR) headset cameras are all part of a global sensor matrix, together allowing us to know anything, anytime, anywhere. This metatrend is driven by the convergence of terrestrial, atmospheric and space-based sensors, vast data networks, and machine learning. In this future, it’s not “what you know,” but rather “the quality of the questions you ask” that will be most important.

(15) Disruption of advertising: As AI becomes increasingly embedded in everyday life, your custom AI will soon understand what you want better than you do. In turn, we will begin to both trust and rely upon our AIs to make most of our buying decisions, turning over shopping to AI-enabled personal assistants. Your AI might make purchases based upon your past desires, current shortages, conversations you’ve allowed your AI to listen to, or by tracking where your pupils focus on a virtual interface (i.e. what catches your attention). As a result, the advertising industry—which normally competes for your attention (whether at the Superbowl or through search engines)—will have a hard time influencing your AI. This metatrend is driven by the convergence of machine learning, sensors, augmented reality, and 5G/networks.

(16) Cellular agriculture moves from the lab into inner cities, providing high-quality protein that is cheaper and healthier: This next decade will witness the birth of the most ethical, nutritious, and environmentally sustainable protein production system devised by humankind. Stem cell-based ‘cellular agriculture’ will allow the production of beef, chicken, and fish anywhere, on-demand, with far higher nutritional content, and a vastly lower environmental footprint than traditional livestock options. This metatrend is enabled by the convergence of biotechnology, materials science, machine learning, and AgTech.

(17) High-bandwidth brain-computer interfaces (BCIs) will come online for public use: Technologist and futurist Ray Kurzweil has predicted that in the mid-2030s, we will begin connecting the human neocortex to the cloud. This next decade will see tremendous progress in that direction, first serving those with spinal cord injuries, whereby patients will regain both sensory capacity and motor control. Yet beyond assisting those with motor function loss, several BCI pioneers are now attempting to supplement their baseline cognitive abilities, a pursuit with the potential to increase their sensorium, memory, and even intelligence. This metatrend is fueled by the convergence of materials science, machine learning, and robotics.

(18) High-resolution VR will transform both retail and real estate shopping: High-resolution, lightweight virtual reality headsets will allow individuals at home to shop for everything from clothing to real estate from the convenience of their living room. Need a new outfit? Your AI knows your detailed body measurements and can whip up a fashion show featuring your avatar wearing the latest 20 designs on a runway. Want to see how your furniture might look inside a house you’re viewing online? No problem! Your AI can populate the property with your virtualized inventory and give you a guided tour. This metatrend is enabled by the convergence of: VR, machine learning, and high-bandwidth networks.

(19) Increased focus on sustainability and the environment: An increase in global environmental awareness and concern over global warming will drive companies to invest in sustainability, both from a necessity standpoint and for marketing purposes. Breakthroughs in materials science, enabled by AI, will allow companies to drive tremendous reductions in waste and environmental contamination. One company’s waste will become another company’s profit center. This metatrend is enabled by the convergence of materials science, artificial intelligence, and broadband networks.

(20) CRISPR and gene therapies will minimize disease: A vast range of infectious diseases, ranging from AIDS to Ebola, are now curable. In addition, gene-editing technologies continue to advance in precision and ease of use, allowing families to treat and ultimately cure hundreds of inheritable genetic diseases. This metatrend is driven by the convergence of various biotechnologies (CRISPR, gene therapy), genome sequencing, and artificial intelligence.

Join Me
(1) A360 Executive Mastermind: If you’re an exponentially and abundance-minded entrepreneur who would like coaching directly from me, consider joining my Abundance 360 Mastermind, a highly selective community of 360 CEOs and entrepreneurs who I coach for 3 days every January in Beverly Hills, Ca. Through A360, I provide my members with context and clarity about how converging exponential technologies will transform every industry. I’m committed to running A360 for the course of an ongoing 25-year journey as a “countdown to the Singularity.”

If you’d like to learn more and consider joining our 2020 membership, apply here.

(2) Abundance-Digital Online Community: I’ve also created a Digital/Online community of bold, abundance-minded entrepreneurs called Abundance-Digital. Abundance-Digital is Singularity University’s ‘onramp’ for exponential entrepreneurs — those who want to get involved and play at a higher level. Click here to learn more.

(Both A360 and Abundance-Digital are part of Singularity University — your participation opens you to a global community.)

This article originally appeared on diamandis.com. Read the original article here.

Image Credit: Image by Free-Photos from Pixabay Continue reading

Posted in Human Robots

#436482 50+ Reasons Our Favorite Emerging ...

For most of history, technology was about atoms, the manipulation of physical stuff to extend humankind’s reach. But in the last five or six decades, atoms have partnered with bits, the elemental “particles” of the digital world as we know it today. As computing has advanced at the accelerating pace described by Moore’s Law, technological progress has become increasingly digitized.

SpaceX lands and reuses rockets and self-driving cars do away with drivers thanks to automation, sensors, and software. Businesses find and hire talent from anywhere in the world, and for better and worse, a notable fraction of the world learns and socializes online. From the sequencing of DNA to artificial intelligence and from 3D printing to robotics, more and more new technologies are moving at a digital pace and quickly emerging to reshape the world around us.

In 2019, stories charting the advances of some of these digital technologies consistently made headlines. Below is, what is at best, an incomplete list of some of the big stories that caught our eye this year. With so much happening, it’s likely we’ve missed some notable headlines and advances—as well as some of your personal favorites. In either instance, share your thoughts and candidates for the biggest stories and breakthroughs on Facebook and Twitter.

With that said, let’s dive straight into the year.

Artificial Intelligence
No technology garnered as much attention as AI in 2019. With good reason. Intelligent computer systems are transitioning from research labs to everyday life. Healthcare, weather forecasting, business process automation, traffic congestion—you name it, and machine learning algorithms are likely beginning to work on it. Yet, AI has also been hyped up and overmarketed, and the latest round of AI technology, deep learning, is likely only one piece of the AI puzzle.

This year, Open AI’s game-playing algorithms beat some of the world’s best Dota 2 players, DeepMind notched impressive wins in Starcraft, and Carnegie Mellon University’s Libratus “crushed” pros at six-player Texas Hold‘em.
Speaking of games, AI’s mastery of the incredibly complex game of Go prompted a former world champion to quit, stating that AI ‘”cannot be defeated.”
But it isn’t just fun and games. Practical, powerful applications that make the best of AI’s pattern recognition abilities are on the way. Insilico Medicine, for example, used machine learning to help discover and design a new drug in just 46 days, and DeepMind is focused on using AI to crack protein folding.
Of course, AI can be a double-edged sword. When it comes to deepfakes and fake news, for example, AI makes both easier to create and detect, and early in the year, OpenAI created and announced a powerful AI text generator but delayed releasing it for fear of malicious use.
Recognizing AI’s power for good and ill, the OECD, EU, World Economic Forum, and China all took a stab at defining an ethical framework for the development and deployment of AI.

Computing Systems
Processors and chips kickstarted the digital boom and are still the bedrock of continued growth. While progress in traditional silicon-based chips continues, it’s slowing and getting more expensive. Some say we’re reaching the end of Moore’s Law. While that may be the case for traditional chips, specialized chips and entirely new kinds of computing are waiting in the wings.

In fall 2019, Google confirmed its quantum computer had achieved “quantum supremacy,” a term that means a quantum computer can perform a calculation a normal computer cannot. IBM pushed back on the claim, and it should be noted the calculation was highly specialized. But while it’s still early days, there does appear to be some real progress (and more to come).
Should quantum computing become truly practical, “the implications are staggering.” It could impact machine learning, medicine, chemistry, and materials science, just to name a few areas.
Specialized chips continue to take aim at machine learning—a giant new chip with over a trillion transistors, for example, may make machine learning algorithms significantly more efficient.
Cellular computers also saw advances in 2019 thanks to CRISPR. And the year witnessed the emergence of the first reprogrammable DNA computer and new chips inspired by the brain.
The development of hardware computing platforms is intrinsically linked to software. 2019 saw a continued move from big technology companies towards open sourcing (at least parts of) their software, potentially democratizing the use of advanced systems.

Networks
Increasing interconnectedness has, in many ways, defined the 21st century so far. Your phone is no longer just a phone. It’s access to the world’s population and accumulated knowledge—and it fits in your pocket. Pretty neat. This is all thanks to networks, which had some notable advances in 2019.

The biggest network development of the year may well be the arrival of the first 5G networks.
5G’s faster speeds promise advances across many emerging technologies.
Self-driving vehicles, for example, may become both smarter and safer thanks to 5G C-V2X networks. (Don’t worry with trying to remember that. If they catch on, they’ll hopefully get a better name.)
Wi-Fi may have heard the news and said “hold my beer,” as 2019 saw the introduction of Wi-Fi 6. Perhaps the most important upgrade, among others, is that Wi-Fi 6 ensures that the ever-growing number of network connected devices get higher data rates.
Networks also went to space in 2019, as SpaceX began launching its Starlink constellation of broadband satellites. In typical fashion, Elon Musk showed off the network’s ability to bounce data around the world by sending a Tweet.

Augmented Reality and Virtual Reality
Forget Pokemon Go (unless you want to add me as a friend in the game—in which case don’t forget Pokemon Go). 2019 saw AR and VR advance, even as Magic Leap, the most hyped of the lot, struggled to live up to outsized expectations and sell headsets.

Mixed reality AR and VR technologies, along with the explosive growth of sensor-based data about the world around us, is creating a one-to-one “Mirror World” of our physical reality—a digital world you can overlay on our own or dive into immersively thanks to AR and VR.
Facebook launched Replica, for example, which is a photorealistic virtual twin of the real world that, among other things, will help train AIs to better navigate their physical surroundings.
Our other senses (beyond eyes) may also become part of the Mirror World through the use of peripherals like a newly developed synthetic skin that aim to bring a sense of touch to VR.
AR and VR equipment is also becoming cheaper—with more producers entering the space—and more user-friendly. Instead of a wired headset requiring an expensive gaming PC, the new Oculus Quest is a wireless, self-contained step toward the mainstream.
Niche uses also continue to gain traction, from Google Glass’s Enterprise edition to the growth of AR and VR in professional education—including on-the-job-training and roleplaying emotionally difficult work encounters, like firing an employee.

Digital Biology and Biotech
The digitization of biology is happening at an incredible rate. With wild new research coming to light every year and just about every tech giant pouring money into new solutions and startups, we’re likely to see amazing advances in 2020 added to those we saw in 2019.

None were, perhaps, more visible than the success of protein-rich, plant-based substitutes for various meats. This was the year Beyond Meat was the top IPO on the NASDAQ stock exchange and people stood in line for the plant-based Impossible Whopper and KFC’s Beyond Chicken.
In the healthcare space, a report about three people with HIV who became virus free thanks to a bone marrow transplants of stem cells caused a huge stir. The research is still in relatively early stages, and isn’t suitable for most people, but it does provides a glimmer of hope.
CRISPR technology, which almost deserves its own section, progressed by leaps and bounds. One tweak made CRISPR up to 50 times more accurate, while the latest new CRISPR-based system, CRISPR prime, was described as a “word processor” for gene editing.
Many areas of healthcare stand to gain from CRISPR. For instance, cancer treatment, were a first safety test showed ‘promising’ results.
CRISPR’s many potential uses, however, also include some weird/morally questionable areas, which was exemplified by one the year’s stranger CRISPR-related stories about a human-monkey hybrid embryo in China.
Incidentally, China could be poised to take the lead on CRISPR thanks to massive investments and research programs.
As a consequence of quick advances in gene editing, we are approaching a point where we will be able to design our own biology—but first we need to have a serious conversation as a society about the ethics of gene editing and what lines should be drawn.

3D Printing
3D printing has quietly been growing both market size and the objects the printers are capable of producing. While both are impressive, perhaps the biggest story of 2019 is their increased speed.

One example was a boat that was printed in just three days, which also set three new world records for 3D printing.
3D printing is also spreading in the construction industry. In Mexico, the technology is being used to construct 50 new homes with subsidized mortgages of just $20/month.
3D printers also took care of all parts of a 640 square-meter home in Dubai.
Generally speaking, the use of 3D printing to make parts for everything from rocket engines (even entire rockets) to trains to cars illustrates the sturdiness of the technology, anno 2019.
In healthcare, 3D printing is also advancing the cause of bio-printed organs and, in one example, was used to print vascularized parts of a human heart.

Robotics
Living in Japan, I get to see Pepper, Aibo, and other robots on pretty much a daily basis. The novelty of that experience is spreading to other countries, and robots are becoming a more visible addition to both our professional and private lives.

We can’t talk about robots and 2019 without mentioning Boston Dynamics’ Spot robot, which went on sale for the general public.
Meanwhile, Google, Boston Dynamics’ former owner, rebooted their robotics division with a more down-to-earth focus on everyday uses they hope to commercialize.
SoftBank’s Pepper robot is working as a concierge and receptionist in various countries. It is also being used as a home companion. Not satisfied, Pepper rounded off 2019 by heading to the gym—to coach runners.
Indeed, there’s a growing list of sports where robots perform as well—or better—than humans.
2019 also saw robots launch an assault on the kitchen, including the likes of Samsung’s robot chef, and invade the front yard, with iRobot’s Terra robotic lawnmower.
In the borderlands of robotics, full-body robotic exoskeletons got a bit more practical, as the (by all accounts) user-friendly, battery-powered Sarcos Robotics Guardian XO went commercial.

Autonomous Vehicles
Self-driving cars did not—if you will forgive the play on words—stay quite on track during 2019. The fallout from Uber’s 2018 fatal crash marred part of the year, while some big players ratcheted back expectations on a quick shift to the driverless future. Still, self-driving cars, trucks, and other autonomous systems did make progress this year.

Winner of my unofficial award for best name in self-driving goes to Optimus Ride. The company also illustrates that self-driving may not be about creating a one-size-fits-all solution but catering to specific markets.
Self-driving trucks had a good year, with tests across many countries and states. One of the year’s odder stories was a self-driving truck traversing the US with a delivery of butter.
A step above the competition may be the future slogan (or perhaps not) of Boeing’s self-piloted air taxi that saw its maiden test flight in 2019. It joins a growing list of companies looking to create autonomous, flying passenger vehicles.
2019 was also the year where companies seemed to go all in on last-mile autonomous vehicles. Who wins that particular competition could well emerge during 2020.

Blockchain and Digital Currencies
Bitcoin continues to be the cryptocurrency equivalent of a rollercoaster, but the underlying blockchain technology is progressing more steadily. Together, they may turn parts of our financial systems cashless and digital—though how and when remains a slightly open question.

One indication of this was Facebook’s hugely controversial announcement of Libra, its proposed cryptocurrency. The company faced immediate pushback and saw a host of partners jump ship. Still, it brought the tech into mainstream conversations as never before and is putting the pressure on governments and central banks to explore their own digital currencies.
Deloitte’s in-depth survey of the state of blockchain highlighted how the technology has moved from fintech into just about any industry you can think of.
One of the biggest issues facing the spread of many digital currencies—Bitcoin in particular, you could argue—is how much energy it consumes to mine them. 2019 saw the emergence of several new digital currencies with a much smaller energy footprint.
2019 was also a year where we saw a new kind of digital currency, stablecoins, rise to prominence. As the name indicates, stablecoins are a group of digital currencies whose price fluctuations are more stable than the likes of Bitcoin.
In a geopolitical sense, 2019 was a year of China playing catch-up. Having initially banned blockchain, the country turned 180 degrees and announced that it was “quite close” to releasing a digital currency and a wave of blockchain-programs.

Renewable Energy and Energy Storage
While not every government on the planet seems to be a fan of renewable energy, it keeps on outperforming fossil fuel after fossil fuel in places well suited to it—even without support from some of said governments.

One of the reasons for renewable energy’s continued growth is that energy efficiency levels keep on improving.
As a result, an increased number of coal plants are being forced to close due to an inability to compete, and the UK went coal-free for a record two weeks.
We are also seeing more and more financial institutions refusing to fund fossil fuel projects. One such example is the European Investment Bank.
Renewable energy’s advance is tied at the hip to the rise of energy storage, which also had a breakout 2019, in part thanks to investments from the likes of Bill Gates.
The size and capabilities of energy storage also grew in 2019. The best illustration came from Australia were Tesla’s mega-battery proved that energy storage has reached a stage where it can prop up entire energy grids.

Image Credit: Mathew Schwartz / Unsplash Continue reading

Posted in Human Robots

#436437 Why AI Will Be the Best Tool for ...

Dmitry Kaminskiy speaks as though he were trying to unload everything he knows about the science and economics of longevity—from senolytics research that seeks to stop aging cells from spewing inflammatory proteins and other molecules to the trillion-dollar life extension industry that he and his colleagues are trying to foster—in one sitting.

At the heart of the discussion with Singularity Hub is the idea that artificial intelligence will be the engine that drives breakthroughs in how we approach healthcare and healthy aging—a concept with little traction even just five years ago.

“At that time, it was considered too futuristic that artificial intelligence and data science … might be more accurate compared to any hypothesis of human doctors,” said Kaminskiy, co-founder and managing partner at Deep Knowledge Ventures, an investment firm that is betting big on AI and longevity.

How times have changed. Artificial intelligence in healthcare is attracting more investments and deals than just about any sector of the economy, according to data research firm CB Insights. In the most recent third quarter, AI healthcare startups raised nearly $1.6 billion, buoyed by a $550 million mega-round from London-based Babylon Health, which uses AI to collect data from patients, analyze the information, find comparable matches, then make recommendations.

Even without the big bump from Babylon Health, AI healthcare startups raised more than $1 billion last quarter, including two companies focused on longevity therapeutics: Juvenescence and Insilico Medicine.

The latter has risen to prominence for its novel use of reinforcement learning and general adversarial networks (GANs) to accelerate the drug discovery process. Insilico Medicine recently published a seminal paper that demonstrated how such an AI system could generate a drug candidate in just 46 days. Co-founder and CEO Alex Zhavoronkov said he believes there is no greater goal in healthcare today—or, really, any venture—than extending the healthy years of the human lifespan.

“I don’t think that there is anything more important than that,” he told Singularity Hub, explaining that an unhealthy society is detrimental to a healthy economy. “I think that it’s very, very important to extend healthy, productive lifespan just to fix the economy.”

An Aging Crisis
The surge of interest in longevity is coming at a time when life expectancy in the US is actually dropping, despite the fact that we spend more money on healthcare than any other nation.

A new paper in the Journal of the American Medical Association found that after six decades of gains, life expectancy for Americans has decreased since 2014, particularly among young and middle-aged adults. While some of the causes are societal, such as drug overdoses and suicide, others are health-related.

While average life expectancy in the US is 78, Kaminskiy noted that healthy life expectancy is about ten years less.

To Zhavoronkov’s point about the economy (a topic of great interest to Kaminskiy as well), the US spent $1.1 trillion on chronic diseases in 2016, according to a report from the Milken Institute, with diabetes, cardiovascular conditions, and Alzheimer’s among the most costly expenses to the healthcare system. When the indirect costs of lost economic productivity are included, the total price tag of chronic diseases in the US is $3.7 trillion, nearly 20 percent of GDP.

“So this is the major negative feedback on the national economy and creating a lot of negative social [and] financial issues,” Kaminskiy said.

Investing in Longevity
That has convinced Kaminskiy that an economy focused on extending healthy human lifespans—including the financial instruments and institutions required to support a long-lived population—is the best way forward.

He has co-authored a book on the topic with Margaretta Colangelo, another managing partner at Deep Knowledge Ventures, which has launched a specialized investment fund, Longevity.Capital, focused on the longevity industry. Kaminskiy estimates that there are now about 20 such investment funds dedicated to funding life extension companies.

In November at the inaugural AI for Longevity Summit in London, he and his collaborators also introduced the Longevity AI Consortium, an academic-industry initiative at King’s College London. Eventually, the research center will include an AI Longevity Accelerator program to serve as a bridge between startups and UK investors.

Deep Knowledge Ventures has committed about £7 million ($9 million) over the next three years to the accelerator program, as well as establishing similar consortiums in other regions of the world, according to Franco Cortese, a partner at Longevity.Capital and director of the Aging Analytics Agency, which has produced a series of reports on longevity.

A Cure for What Ages You
One of the most recent is an overview of Biomarkers for Longevity. A biomarker, in the case of longevity, is a measurable component of health that can indicate a disease state or a more general decline in health associated with aging. Examples range from something as simple as BMI as an indicator of obesity, which is associated with a number of chronic diseases, to sophisticated measurements of telomeres, the protective ends of chromosomes that shorten as we age.

While some researchers are working on moonshot therapies to reverse or slow aging—with a few even arguing we could expand human life on the order of centuries—Kaminskiy said he believes understanding biomarkers of aging could make more radical interventions unnecessary.

In this vision of healthcare, people would be able to monitor their health 24-7, with sensors attuned to various biomarkers that could indicate the onset of everything from the flu to diabetes. AI would be instrumental in not just ingesting the billions of data points required to develop such a system, but also what therapies, treatments, or micro-doses of a drug or supplement would be required to maintain homeostasis.

“Consider it like Tesla with many, many detectors, analyzing the behavior of the car in real time, and a cloud computing system monitoring those signals in real time with high frequency,” Kaminskiy explained. “So the same shall be applied for humans.”

And only sophisticated algorithms, Kaminskiy argued, can make longevity healthcare work on a mass scale but at the individual level. Precision medicine becomes preventive medicine. Healthcare truly becomes a system to support health rather than a way to fight disease.

Image Credit: Photo by h heyerlein on Unsplash Continue reading

Posted in Human Robots