Tag Archives: back

#436774 AI Is an Energy-Guzzler. We Need to ...

There is a saying that has emerged among the tech set in recent years: AI is the new electricity. The platitude refers to the disruptive power of artificial intelligence for driving advances in everything from transportation to predicting the weather.

Of course, the computers and data centers that support AI’s complex algorithms are very much dependent on electricity. While that may seem pretty obvious, it may be surprising to learn that AI can be extremely power-hungry, especially when it comes to training the models that enable machines to recognize your face in a photo or for Alexa to understand a voice command.

The scale of the problem is difficult to measure, but there have been some attempts to put hard numbers on the environmental cost.

For instance, one paper published on the open-access repository arXiv claimed that the carbon emissions for training a basic natural language processing (NLP) model—algorithms that process and understand language-based data—are equal to the CO2 produced by the average American lifestyle over two years. A more robust model required the equivalent of about 17 years’ worth of emissions.

The authors noted that about a decade ago, NLP models could do the job on a regular commercial laptop. Today, much more sophisticated AI models use specialized hardware like graphics processing units, or GPUs, a chip technology popularized by Nvidia for gaming that also proved capable of supporting computing tasks for AI.

OpenAI, a nonprofit research organization co-founded by tech prophet and profiteer Elon Musk, said that the computing power “used in the largest AI training runs has been increasing exponentially with a 3.4-month doubling time” since 2012. That’s about the time that GPUs started making their way into AI computing systems.

Getting Smarter About AI Chip Design
While GPUs from Nvidia remain the gold standard in AI hardware today, a number of startups have emerged to challenge the company’s industry dominance. Many are building chipsets designed to work more like the human brain, an area that’s been dubbed neuromorphic computing.

One of the leading companies in this arena is Graphcore, a UK startup that has raised more than $450 million and boasts a valuation of $1.95 billion. The company’s version of the GPU is an IPU, which stands for intelligence processing unit.

To build a computer brain more akin to a human one, the big brains at Graphcore are bypassing the precise but time-consuming number-crunching typical of a conventional microprocessor with one that’s content to get by on less precise arithmetic.

The results are essentially the same, but IPUs get the job done much quicker. Graphcore claimed it was able to train the popular BERT NLP model in just 56 hours, while tripling throughput and reducing latency by 20 percent.

An article in Bloomberg compared the approach to the “human brain shifting from calculating the exact GPS coordinates of a restaurant to just remembering its name and neighborhood.”

Graphcore’s hardware architecture also features more built-in memory processing, boosting efficiency because there’s less need to send as much data back and forth between chips. That’s similar to an approach adopted by a team of researchers in Italy that recently published a paper about a new computing circuit.

The novel circuit uses a device called a memristor that can execute a mathematical function known as a regression in just one operation. The approach attempts to mimic the human brain by processing data directly within the memory.

Daniele Ielmini at Politecnico di Milano, co-author of the Science Advances paper, told Singularity Hub that the main advantage of in-memory computing is the lack of any data movement, which is the main bottleneck of conventional digital computers, as well as the parallel processing of data that enables the intimate interactions among various currents and voltages within the memory array.

Ielmini explained that in-memory computing can have a “tremendous impact on energy efficiency of AI, as it can accelerate very advanced tasks by physical computation within the memory circuit.” He added that such “radical ideas” in hardware design will be needed in order to make a quantum leap in energy efficiency and time.

It’s Not Just a Hardware Problem
The emphasis on designing more efficient chip architecture might suggest that AI’s power hunger is essentially a hardware problem. That’s not the case, Ielmini noted.

“We believe that significant progress could be made by similar breakthroughs at the algorithm and dataset levels,” he said.

He’s not the only one.

One of the key research areas at Qualcomm’s AI research lab is energy efficiency. Max Welling, vice president of Qualcomm Technology R&D division, has written about the need for more power-efficient algorithms. He has gone so far as to suggest that AI algorithms will be measured by the amount of intelligence they provide per joule.

One emerging area being studied, Welling wrote, is the use of Bayesian deep learning for deep neural networks.

It’s all pretty heady stuff and easily the subject of a PhD thesis. The main thing to understand in this context is that Bayesian deep learning is another attempt to mimic how the brain processes information by introducing random values into the neural network. A benefit of Bayesian deep learning is that it compresses and quantifies data in order to reduce the complexity of a neural network. In turn, that reduces the number of “steps” required to recognize a dog as a dog—and the energy required to get the right result.

A team at Oak Ridge National Laboratory has previously demonstrated another way to improve AI energy efficiency by converting deep learning neural networks into what’s called a spiking neural network. The researchers spiked their deep spiking neural network (DSNN) by introducing a stochastic process that adds random values like Bayesian deep learning.

The DSNN actually imitates the way neurons interact with synapses, which send signals between brain cells. Individual “spikes” in the network indicate where to perform computations, lowering energy consumption because it disregards unnecessary computations.

The system is being used by cancer researchers to scan millions of clinical reports to unearth insights on causes and treatments of the disease.

Helping battle cancer is only one of many rewards we may reap from artificial intelligence in the future, as long as the benefits of those algorithms outweigh the costs of using them.

“Making AI more energy-efficient is an overarching objective that spans the fields of algorithms, systems, architecture, circuits, and devices,” Ielmini said.

Image Credit: analogicus from Pixabay 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

#436507 The Weird, the Wacky, the Just Plain ...

As you know if you’ve ever been to, heard of, or read about the annual Consumer Electronics Show in Vegas, there’s no shortage of tech in any form: gadgets, gizmos, and concepts abound. You probably couldn’t see them all in a month even if you spent all day every day trying.

Given the sheer scale of the show, the number of exhibitors, and the inherent subjectivity of bestowing superlatives, it’s hard to pick out the coolest tech from CES. But I’m going to do it anyway; in no particular order, here are some of the products and concepts that I personally found most intriguing at this year’s event.

e-Novia’s Haptic Gloves
Italian startup e-Novia’s Weart glove uses a ‘sensing core’ to record tactile sensations and an ‘actuation core’ to reproduce those sensations onto the wearer’s skin. Haptic gloves will bring touch to VR and AR experiences, making them that much more life-like. The tech could also be applied to digitization of materials and in gaming and entertainment.

e-Novia’s modular haptic glove
I expected a full glove, but in fact there were two rings that attached to my fingers. Weart co-founder Giovanni Spagnoletti explained that they’re taking a modular approach, so as to better tailor the technology to different experiences. He then walked me through a virtual reality experience that was a sort of simulated science experiment: I had to lift a glass beaker, place it on a stove, pour in an ingredient, open a safe to access some dry ice, add that, and so on. As I went through the steps, I felt the beaker heat up and cool off at the expected times, and felt the liquid moving inside, as well as the pressure of my fingertips against the numbered buttons on the safe.

A virtual (but tactile) science experiment
There was a slight delay between my taking an action and feeling the corresponding tactile sensation, but on the whole, the haptic glove definitely made the experience more realistic—and more fun. Slightly less fun but definitely more significant, Spagnoletti told me Weart is working with a medical group to bring tactile sensations to VR training for surgeons.

Sarcos Robotics’ Exoskeleton
That tire may as well be a feather
Sarcos Robotics unveiled its Guardian XO full-body exoskeleton, which it says can safely lift up to 200 pounds across an extended work session. What’s cool about this particular exoskeleton is that it’s not just a prototype; the company announced a partnership with Delta airlines, which will be trialing the technology for aircraft maintenance, engine repair, and luggage handling. In a demo, I watched a petite female volunteer strap into the exoskeleton and easily lift a 50-pound weight with one hand, and a Sarcos employee lift and attach a heavy component of a propeller; she explained that the strength-augmenting function of the exoskeleton can easily be switched on or off—and the wearer’s hands released—to facilitate multi-step tasks.

Hyundai’s Flying Taxi
Where to?
Hyundai and Uber partnered to unveil an air taxi concept. With a 49-foot wingspan, 4 lift rotors, and 4 tilt rotors, the aircraft would be manned by a pilot and could carry 4 passengers at speeds up to 180 miles per hour. The companies say you’ll be able to ride across your city in one of these by 2030—we’ll see if the regulatory environment, public opinion, and other factors outside of technological capability let that happen.

Mercedes’ Avatar Concept Car
Welcome to the future
As evident from its name, Mercedes’ sweet new Vision AVTR concept car was inspired by the movie Avatar; director James Cameron helped design it. The all-electric car has no steering wheel, transparent doors, seats made of vegan leather, and 33 reptilian-scale-like flaps on the back; its design is meant to connect the driver with both the car and the surrounding environment in a natural, seamless way.

Next-generation scrolling
Offered the chance to ‘drive’ the car, I jumped on it. Placing my hand on the center console started the engine, and within seconds it had synced to my heartbeat, which reverberated through the car. The whole dashboard, from driver door to passenger door, is one big LED display. It showed a virtual landscape I could select by holding up my hand: as I moved my hand from left to right, different images were projected onto my open palm. Closing my hand on an image selected it, and suddenly it looked like I was in the middle of a lush green mountain range. Applying slight forward pressure on the center console made the car advance in the virtual landscape; it was essentially like playing a really cool video game.

Mercedes is aiming to have a carbon-neutral production fleet by 2039, and to reduce the amount of energy it uses during production by 40 percent by 2030. It’s unclear when—or whether—the man-machine-nature connecting features of the Vision AVTR will start showing up in production, but I for one will be on the lookout.

Waverly Labs’ In-Ear Translator
Waverly Labs unveiled its Ambassador translator earlier this year and has it on display at the show. It’s worn on the ear and uses a far-field microphone array with speech recognition to translate real-time conversations in 20 different languages. Besides in-ear audio, translations can also appear as text on an app or be broadcast live in a conference environment.

It’s kind of like a giant talking earring
I stopped by the booth and tested out the translator with Waverly senior software engineer Georgiy Konovalov. We each hooked on an earpiece, and first, he spoke to me in Russian. After a delay of a couple seconds, I heard his words in—slightly robotic, but fully comprehensible—English. Then we switched: I spoke to him in Spanish, my words popped up on his phone screen in Cyrillic, and he translated them back to English for me out loud.

On the whole, the demo was pretty cool. If you’ve ever been lost in a foreign country whose language you don’t speak, imagine how handy a gadget like this would come in. Let’s just hope that once they’re more widespread, these products don’t end up discouraging people from learning languages.

Not to be outdone, Google also announced updates to its Translate product, which is being deployed at information desks in JFK airport’s international terminal, in sports stadiums in Qatar, and by some large hotel chains.

Stratuscent’s Digital Nose
AI is making steady progress towards achieving human-like vision and hearing—but there’s been less work done on mimicking our sense of smell (maybe because it’s less useful in everyday applications). Stratuscent’s digital nose, which it says is based on NASA patents, uses chemical receptors and AI to identify both simple chemicals and complex scents. The company is aiming to create the world’s first comprehensive database of everyday scents, which it says it will use to make “intelligent decisions” for customers. What kind of decisions remains to be seen—and smelled.

Banner Image Credit: The Mercedes Vision AVTR concept car. Photo by Vanessa Bates Ramirez Continue reading

Posted in Human Robots

#436491 The Year’s Most Fascinating Tech ...

Last Saturday we took a look at some of the most-read Singularity Hub articles from 2019. This week, we’re featuring some of our favorite articles from the last year. As opposed to short pieces about what’s happening, these are long reads about why it matters and what’s coming next. Some of them make the news while others frame the news, go deep on big ideas, go behind the scenes, or explore the human side of technological progress.

We hope you find them as fascinating, inspiring, and illuminating as we did.

DeepMind and Google: The Battle to Control Artificial Intelligence
Hal Hodson | 1843
“[DeepMind cofounder and CEO Demis] Hassabis thought DeepMind would be a hybrid: it would have the drive of a startup, the brains of the greatest universities, and the deep pockets of one of the world’s most valuable companies. Every element was in place to hasten the arrival of [artificial general intelligence] and solve the causes of human misery.”

The Most Powerful Person in Silicon Valley
Katrina Brooker | Fast Company
“Billionaire Masayoshi Son—not Elon Musk, Jeff Bezos, or Mark Zuckerberg—has the most audacious vision for an AI-powered utopia where machines control how we live. And he’s spending hundreds of billions of dollars to realize it. Are you ready to live in Masa World?”

AR Will Spark the Next Big Tech Platform—Call It Mirrorworld
Kevin Kelly | Wired
“Eventually this melded world will be the size of our planet. It will be humanity’s greatest achievement, creating new levels of wealth, new social problems, and uncountable opportunities for billions of people. There are no experts yet to make this world; you are not late.”

Behind the Scenes of a Radical New Cancer Cure
Ilana Yurkiewicz | Undark
“I remember the first time I watched a patient get his Day 0 infusion. It felt anti-climactic. The entire process took about 15 minutes. The CAR-T cells are invisible to the naked eye, housed in a small plastic bag containing clear liquid. ‘That’s it?’ my patient asked when the nurse said it was over. The infusion part is easy. The hard part is everything that comes next.”

The Promise and Price of Cellular Therapies
Siddhartha Mukherjee | The New Yorker
“We like to imagine medical revolutions as, well, revolutionary—propelled forward through leaps of genius and technological innovation. But they are also evolutionary, nudged forward through the optimization of design and manufacture.”

Impossible Foods’ Rising Empire of Almost Meat
Chris Ip | Engadget
“Impossible says it wants to ultimately create a parallel universe of ersatz animal products from steak to eggs. …Yet as Impossible ventures deeper into the culinary uncanny valley, it also needs society to discard a fundamental cultural idea that dates back millennia and accept a new truth: Meat doesn’t have to come from animals.”

Inside the Amazon Warehouse Where Humans and Machines Become One
Matt Simon | Wired
“Seen from above, the scale of the system is dizzying. My robot, a little orange slab known as a ‘drive’ (or more formally and mythically, Pegasus), is just one of hundreds of its kind swarming a 125,000-square-foot ‘field’ pockmarked with chutes. It’s a symphony of electric whirring, with robots pausing for one another at intersections and delivering their packages to the slides.”

Boston Dynamics’ Robots Are Preparing to Leave the Lab—Is the World Ready?
James Vincent | The Verge
“After decades of kicking machines in parking lots, the company is set to launch its first ever commercial bot later this year: the quadrupedal Spot. It’s a crucial test for a company that’s spent decades pursuing long-sighted R&D. And more importantly, the success—or failure—of Spot will tell us a lot about our own robot future. Are we ready for machines to walk among us?”

I Cut the ‘Big Five’ Tech Giants From My Life. It Was Hell
Kashmir Hill | Gizmodo
“Critics of the big tech companies are often told, ‘If you don’t like the company, don’t use its products.’ I did this experiment to find out if that is possible, and I found out that it’s not—with the exception of Apple. …These companies are unavoidable because they control internet infrastructure, online commerce, and information flows.”

Why I (Still) Love Tech: In Defense of a Difficult Industry
Paul Ford | Wired
“The mysteries of software caught my eye when I was a boy, and I still see it with the same wonder, even though I’m now an adult. Proudshamed, yes, but I still love it, the mess of it, the code and toolkits, down to the pixels and the processors, and up to the buses and bridges. I love the whole made world. But I can’t deny that the miracle is over, and that there is an unbelievable amount of work left for us to do.”

The Peculiar Blindness of Experts
David Epstein | The Atlantic
“In business, esteemed (and lavishly compensated) forecasters routinely are wildly wrong in their predictions of everything from the next stock-market correction to the next housing boom. Reliable insight into the future is possible, however. It just requires a style of thinking that’s uncommon among experts who are certain that their deep knowledge has granted them a special grasp of what is to come.”

The Most Controversial Tree in the World
Rowan Jacobson | Pacific Standard
“…we are all GMOs, the beneficiaries of freakishly unlikely genetic mash-ups, and the real Island of Dr. Moreau is that blue-green botanical garden positioned third from the sun. Rather than changing the nature of nature, as I once thought, this might just be the very nature of nature.”

How an Augmented Reality Game Escalated Into Real-World Spy Warfare
Elizabeth Ballou | Vice
“In Ingress, players accept that every park and train station could be the site of an epic showdown, but that’s only the first step. The magic happens when other people accept that, too. When players feel like that magic is real, there are few limits to what they’ll do or where they’ll go for the sake of the game. ”

The Shady Cryptocurrency Boom on the Post-Soviet Frontier
Hannah Lucinda Smith | Wired
“…although the tourists won’t guess it as they stand at Kuchurgan’s gates, admiring how the evening light reflects off the silver plaque of Lenin, this plant is pumping out juice to a modern-day gold rush: a cryptocurrency boom that is underway all across the former Soviet Union, from the battlefields of eastern Ukraine to time-warp enclaves like Transnistria and freshly annexed Crimea.”

Scientists Are Totally Rethinking Animal Cognition
Ross Andersen | The Atlantic
“This idea that animals are conscious was long unpopular in the West, but it has lately found favor among scientists who study animal cognition. …For many scientists, the resonant mystery is no longer which animals are conscious, but which are not.”

I Wrote This on a 30-Year-Old Computer
Ian Bogost | The Atlantic
“[Back then] computing was an accompaniment to life, rather than the sieve through which all ideas and activities must filter. That makes using this 30-year-old device a surprising joy, one worth longing for on behalf of what it was at the time, rather than for the future it inaugurated.”

Image Credit: Wes Hicks / Unsplash Continue reading

Posted in Human Robots

#436488 Tech’s Biggest Leaps From the Last 10 ...

As we enter our third decade in the 21st century, it seems appropriate to reflect on the ways technology developed and note the breakthroughs that were achieved in the last 10 years.

The 2010s saw IBM’s Watson win a game of Jeopardy, ushering in mainstream awareness of machine learning, along with DeepMind’s AlphaGO becoming the world’s Go champion. It was the decade that industrial tools like drones, 3D printers, genetic sequencing, and virtual reality (VR) all became consumer products. And it was a decade in which some alarming trends related to surveillance, targeted misinformation, and deepfakes came online.

For better or worse, the past decade was a breathtaking era in human history in which the idea of exponential growth in information technologies powered by computation became a mainstream concept.

As I did last year for 2018 only, I’ve asked a collection of experts across the Singularity University faculty to help frame the biggest breakthroughs and moments that gave shape to the past 10 years. I asked them what, in their opinion, was the most important breakthrough in their respective fields over the past decade.

My own answer to this question, focused in the space of augmented and virtual reality, would be the stunning announcement in March of 2014 that Facebook acquired Oculus VR for $2 billion. Although VR technology had been around for a while, it was at this precise moment that VR arrived as a consumer technology platform. Facebook, largely fueled by the singular interest of CEO Mark Zuckerberg, has funded the development of this industry, keeping alive the hope that consumer VR can become a sustainable business. In the meantime, VR has continued to grow in sophistication and usefulness, though it has yet to truly take off as a mainstream concept. That will hopefully be a development for the 2020s.

Below is a decade in review across the technology areas that are giving shape to our modern world, as described by the SU community of experts.

Digital Biology
Dr. Tiffany Vora | Faculty Director and Vice Chair, Digital Biology and Medicine, Singularity University

In my mind, this decade of astounding breakthroughs in the life sciences and medicine rests on the achievement of the $1,000 human genome in 2016. More-than-exponentially falling costs of DNA sequencing have driven advances in medicine, agriculture, ecology, genome editing, synthetic biology, the battle against climate change, and our fundamental understanding of life and its breathtaking connections. The “digital” revolution in DNA constituted an important model for harnessing other types of biological information, from personalized bio data to massive datasets spanning populations and species.

Crucially, by aggressively driving down the cost of such analyses, researchers and entrepreneurs democratized access to the source code of life—with attendant financial, cultural, and ethical consequences. Exciting, but take heed: Veritas Genetics spearheaded a $600 genome in 2019, only to have to shutter USA operations due to a money trail tangled with the trade war with China. Stay tuned through the early 2020s to see the pricing of DNA sequencing fall even further … and to experience the many ways that cheaper, faster harvesting of biological data will enrich your daily life.

Cryptocurrency
Alex Gladstein | Chief Strategy Officer, Human Rights Foundation

The past decade has seen Bitcoin go from just an idea on an obscure online message board to a global financial network carrying more than 100 billion dollars in value. And we’re just getting started. One recent defining moment in the cryptocurrency space has been a stunning trend underway in Venezuela, where today, the daily dollar-denominated value of Bitcoin traded now far exceeds the daily dollar-denominated value traded on the Caracas Stock Exchange. It’s just one country, but it’s a significant country, and a paradigm shift.

Governments and corporations are following Bitcoin’s success too, and are looking to launch their own digital currencies. China will launch its “DC/EP” project in the coming months, and Facebook is trying to kickstart its Libra project. There are technical and regulatory uncertainties for both, but one thing is for certain: the era of digital currency has arrived.

Business Strategy and Entrepreneurship
Pascal Finnette | Chair, Entrepreneurship and Open Innovation, Singularity University

For me, without a doubt, the most interesting and quite possibly ground-shifting development in the fields of entrepreneurship and corporate innovation in the last ten years is the rapid maturing of customer-driven product development frameworks such as Lean Startup, and its subsequent adoption by corporates for their own innovation purposes.

Tools and frameworks like the Business Model Canvas, agile (software) development and the aforementioned Lean Startup methodology fundamentally shifted the way we think and go about building products, services, and companies, with many of these tools bursting onto the startup scene in the late 2000s and early 2010s.

As these tools matured they found mass adoption not only in startups around the world, but incumbent companies who eagerly adopted them to increase their own innovation velocity and success.

Energy
Ramez Naam | Co-Chair, Energy and Environment, Singularity University

The 2010s were the decade that saw clean electricity, energy storage, and electric vehicles break through price and performance barriers around the world. Solar, wind, batteries, and EVs started this decade as technologies that had to be subsidized. That was the first phase of their existence. Now they’re entering their third, most disruptive phase, where shifting to clean energy and mobility is cheaper than continuing to use existing coal, gas, or oil infrastructure.

Consider that at the start of 2010, there was no place on earth where building new solar or wind was cheaper than building new coal or gas power generation. By 2015, in some of the sunniest and windiest places on earth, solar and wind had entered their second phase, where they were cost-competitive for new power. And then, in 2018 and 2019, we started to see the edge of the third phase, as building new solar and wind, in some parts of the world, was cheaper than operating existing coal or gas power plants.

Food Technology
Liz Specht, Ph. D | Associate Director of Science & Technology, The Good Food Institute

The arrival of mainstream plant-based meat is easily the food tech advance of the decade. Meat analogs have, of course, been around forever. But only in the last decade have companies like Beyond Meat and Impossible Foods decided to cut animals out of the process and build no-compromise meat directly from plants.

Plant-based meat is already transforming the fast-food industry. For example, the introduction of the Impossible Whopper led Burger King to their most profitable quarter in many years. But the global food industry as a whole is shifting as well. Tyson, JBS, Nestle, Cargill, and many others are all embracing plant-based meat.

Augmented and Virtual Reality
Jody Medich | CEO, Superhuman-x

The breakthrough moment for augmented and virtual reality came in 2013 when Palmer Lucky took apart an Android smartphone and added optic lenses to make the first version of the Oculus Rift. Prior to that moment, we struggled with miniaturizing the components needed to develop low-latency head-worn devices. But thanks to the smartphone race started in 2006 with the iPhone, we finally had a suite of sensors, chips, displays, and computing power small enough to put on the head.

What will the next 10 years bring? Look for AR/VR to explode in a big way. We are right on the cusp of that tipping point when the tech is finally “good enough” for our linear expectations. Given all it can do today, we can’t even picture what’s possible. Just as today we can’t function without our phones, by 2029 we’ll feel lost without some AR/VR product. It will be the way we interact with computing, smart objects, and AI. Tim Cook, Apple CEO, predicts it will replace all of today’s computing devices. I can’t wait.

Philosophy of Technology
Alix Rübsaam | Faculty Fellow, Singularity University, Philosophy of Technology/Ethics of AI

The last decade has seen a significant shift in our general attitude towards the algorithms that we now know dictate much of our surroundings. Looking back at the beginning of the decade, it seems we were blissfully unaware of how the data we freely and willingly surrendered would feed the algorithms that would come to shape every aspect of our daily lives: the news we consume, the products we purchase, the opinions we hold, etc.

If I were to isolate a single publication that contributed greatly to the shift in public discourse on algorithms, it would have to be Cathy O’Neil’s Weapons of Math Destruction from 2016. It remains a comprehensive, readable, and highly informative insight into how algorithms dictate our finances, our jobs, where we go to school, or if we can get health insurance. Its publication represents a pivotal moment when the general public started to question whether we should be OK with outsourcing decision making to these opaque systems.

The ubiquity of ethical guidelines for AI and algorithms published just in the last year (perhaps most comprehensively by the AI Now Institute) fully demonstrates the shift in public opinion of this decade.

Data Science
Ola Kowalewski | Faculty Fellow, Singularity University, Data Innovation

In the last decade we entered the era of internet and smartphone ubiquity. The number of internet users doubled, with nearly 60 percent of the global population connected online and now over 35 percent of the globe owns a smartphone. With billions of people in a state of constant connectedness and therefore in a state of constant surveillance, the companies that have built the tech infrastructure and information pipelines have dominated the global economy. This shift from tech companies being the underdogs to arguably the world’s major powers sets the landscape we enter for the next decade.

Global Grand Challenges
Darlene Damm | Vice Chair, Faculty, Global Grand Challenges, Singularity University

The biggest breakthrough over the last decade in social impact and technology is that the social impact sector switched from seeing technology as something problematic to avoid, to one of the most effective ways to create social change. We now see people using exponential technologies to solve all sorts of social challenges in areas ranging from disaster response to hunger to shelter.

The world’s leading social organizations, such as UNICEF and the World Food Programme, have launched their own venture funds and accelerators, and the United Nations recently declared that digitization is revolutionizing global development.

Digital Biology
Raymond McCauley | Chair, Digital Biology, Singularity University, Co-Founder & Chief Architect, BioCurious; Principal, Exponential Biosciences

CRISPR is bringing about a revolution in genetic engineering. It’s obvious, and it’s huge. What may not be so obvious is the widespread adoption of genetic testing. And this may have an even longer-lasting effect. It’s used to test new babies, to solve medical mysteries, and to catch serial killers. Thanks to holiday ads from 23andMe and Ancestry.com, it’s everywhere. Testing your DNA is now a common over-the-counter product. People are using it to set their diet, to pick drugs, and even for dating (or at least picking healthy mates).

And we’re just in the early stages. Further down the line, doing large-scale studies on more people, with more data, will lead to the use of polygenic risk scores to help us rank our genetic potential for everything from getting cancer to being a genius. Can you imagine what it would be like for parents to pick new babies, GATTACA-style, to get the smartest kids? You don’t have to; it’s already happening.

Artificial Intelligence
Neil Jacobstein | Chair, Artificial Intelligence and Robotics, Singularity University

The convergence of exponentially improved computing power, the deep learning algorithm, and access to massive data resulted in a series of AI breakthroughs over the past decade. These included: vastly improved accuracy in identifying images, making self driving cars practical, beating several world champions in Go, and identifying gender, smoking status, and age from retinal fundus photographs.

Combined, these breakthroughs convinced researchers and investors that after 50+ years of research and development, AI was ready for prime-time applications. Now, virtually every field of human endeavor is being revolutionized by machine learning. We still have a long way to go to achieve human-level intelligence and beyond, but the pace of worldwide improvement is blistering.

Hod Lipson | Professor of Engineering and Data Science, Columbia University

The biggest moment in AI in the past decade (and in its entire history, in my humble opinion) was midnight, Pacific time, September 30, 2012: the moment when machines finally opened their eyes. It was the moment when deep learning took off, breaking stagnant decades of machine blindness, when AI couldn’t reliably tell apart even a cat from a dog. That seemingly trivial accomplishment—a task any one-year-old child can do—has had a ripple effect on AI applications from driverless cars to health diagnostics. And this is just the beginning of what is sure to be a Cambrian explosion of AI.

Neuroscience
Divya Chander | Chair, Neuroscience, Singularity University

If the 2000s were the decade of brain mapping, then the 2010s were the decade of brain writing. Optogenetics, a technique for precisely mapping and controlling neurons and neural circuits using genetically-directed light, saw incredible growth in the 2010s.

Also in the last 10 years, neuromodulation, or the ability to rewire the brain using both invasive and non-invasive interfaces and energy, has exploded in use and form. For instance, the Braingate consortium showed us how electrode arrays implanted into the motor cortex could be used by paralyzed people to use their thoughts to direct a robotic arm. These technologies, alone or in combination with robotics, exoskeletons, and flexible, implantable, electronics also make possible a future of human augmentation.

Image Credit: Image by Jorge Guillen from Pixabay Continue reading

Posted in Human Robots