Tag Archives: Processing

#437171 Scientists Tap the World’s Most ...

In The Hitchhiker’s Guide to the Galaxy by Douglas Adams, the haughty supercomputer Deep Thought is asked whether it can find the answer to the ultimate question concerning life, the universe, and everything. It replies that, yes, it can do it, but it’s tricky and it’ll have to think about it. When asked how long it will take it replies, “Seven-and-a-half million years. I told you I’d have to think about it.”

Real-life supercomputers are being asked somewhat less expansive questions but tricky ones nonetheless: how to tackle the Covid-19 pandemic. They’re being used in many facets of responding to the disease, including to predict the spread of the virus, to optimize contact tracing, to allocate resources and provide decisions for physicians, to design vaccines and rapid testing tools, and to understand sneezes. And the answers are needed in a rather shorter time frame than Deep Thought was proposing.

The largest number of Covid-19 supercomputing projects involves designing drugs. It’s likely to take several effective drugs to treat the disease. Supercomputers allow researchers to take a rational approach and aim to selectively muzzle proteins that SARS-CoV-2, the virus that causes Covid-19, needs for its life cycle.

The viral genome encodes proteins needed by the virus to infect humans and to replicate. Among these are the infamous spike protein that sniffs out and penetrates its human cellular target, but there are also enzymes and molecular machines that the virus forces its human subjects to produce for it. Finding drugs that can bind to these proteins and stop them from working is a logical way to go.

The Summit supercomputer at Oak Ridge National Laboratory has a peak performance of 200,000 trillion calculations per second—equivalent to about a million laptops. Image credit: Oak Ridge National Laboratory, U.S. Dept. of Energy, CC BY

I am a molecular biophysicist. My lab, at the Center for Molecular Biophysics at the University of Tennessee and Oak Ridge National Laboratory, uses a supercomputer to discover drugs. We build three-dimensional virtual models of biological molecules like the proteins used by cells and viruses, and simulate how various chemical compounds interact with those proteins. We test thousands of compounds to find the ones that “dock” with a target protein. Those compounds that fit, lock-and-key style, with the protein are potential therapies.

The top-ranked candidates are then tested experimentally to see if they indeed do bind to their targets and, in the case of Covid-19, stop the virus from infecting human cells. The compounds are first tested in cells, then animals, and finally humans. Computational drug discovery with high-performance computing has been important in finding antiviral drugs in the past, such as the anti-HIV drugs that revolutionized AIDS treatment in the 1990s.

World’s Most Powerful Computer
Since the 1990s the power of supercomputers has increased by a factor of a million or so. Summit at Oak Ridge National Laboratory is presently the world’s most powerful supercomputer, and has the combined power of roughly a million laptops. A laptop today has roughly the same power as a supercomputer had 20-30 years ago.

However, in order to gin up speed, supercomputer architectures have become more complicated. They used to consist of single, very powerful chips on which programs would simply run faster. Now they consist of thousands of processors performing massively parallel processing in which many calculations, such as testing the potential of drugs to dock with a pathogen or cell’s proteins, are performed at the same time. Persuading those processors to work together harmoniously is a pain in the neck but means we can quickly try out a lot of chemicals virtually.

Further, researchers use supercomputers to figure out by simulation the different shapes formed by the target binding sites and then virtually dock compounds to each shape. In my lab, that procedure has produced experimentally validated hits—chemicals that work—for each of 16 protein targets that physician-scientists and biochemists have discovered over the past few years. These targets were selected because finding compounds that dock with them could result in drugs for treating different diseases, including chronic kidney disease, prostate cancer, osteoporosis, diabetes, thrombosis and bacterial infections.

Scientists are using supercomputers to find ways to disable the various proteins—including the infamous spike protein (green protrusions)—produced by SARS-CoV-2, the virus responsible for Covid-19. Image credit: Thomas Splettstoesser scistyle.com, CC BY-ND

Billions of Possibilities
So which chemicals are being tested for Covid-19? A first approach is trying out drugs that already exist for other indications and that we have a pretty good idea are reasonably safe. That’s called “repurposing,” and if it works, regulatory approval will be quick.

But repurposing isn’t necessarily being done in the most rational way. One idea researchers are considering is that drugs that work against protein targets of some other virus, such as the flu, hepatitis or Ebola, will automatically work against Covid-19, even when the SARS-CoV-2 protein targets don’t have the same shape.

Our own work has now expanded to about 10 targets on SARS-CoV-2, and we’re also looking at human protein targets for disrupting the virus’s attack on human cells. Top-ranked compounds from our calculations are being tested experimentally for activity against the live virus. Several of these have already been found to be active.The best approach is to check if repurposed compounds will actually bind to their intended target. To that end, my lab published a preliminary report of a supercomputer-driven docking study of a repurposing compound database in mid-February. The study ranked 8,000 compounds in order of how well they bind to the viral spike protein. This paper triggered the establishment of a high-performance computing consortium against our viral enemy, announced by President Trump in March. Several of our top-ranked compounds are now in clinical trials.

Also, we and others are venturing out into the wild world of new drug discovery for Covid-19—looking for compounds that have never been tried as drugs before. Databases of billions of these compounds exist, all of which could probably be synthesized in principle but most of which have never been made. Billion-compound docking is a tailor-made task for massively parallel supercomputing.

Dawn of the Exascale Era
Work will be helped by the arrival of the next big machine at Oak Ridge, called Frontier, planned for next year. Frontier should be about 10 times more powerful than Summit. Frontier will herald the “exascale” supercomputing era, meaning machines capable of 1,000,000,000,000,000,000 calculations per second.

Although some fear supercomputers will take over the world, for the time being, at least, they are humanity’s servants, which means that they do what we tell them to. Different scientists have different ideas about how to calculate which drugs work best—some prefer artificial intelligence, for example—so there’s quite a lot of arguing going on.

Hopefully, scientists armed with the most powerful computers in the world will, sooner rather than later, find the drugs needed to tackle Covid-19. If they do, then their answers will be of more immediate benefit, if less philosophically tantalizing, than the answer to the ultimate question provided by Deep Thought, which was, maddeningly, simply 42.

This article is republished from The Conversation under a Creative Commons license. Read the original article.

Image credit: NIH/NIAID Continue reading

Posted in Human Robots

#436911 Scientists Linked Artificial and ...

Scientists have linked up two silicon-based artificial neurons with a biological one across multiple countries into a fully-functional network. Using standard internet protocols, they established a chain of communication whereby an artificial neuron controls a living, biological one, and passes on the info to another artificial one.

Whoa.

We’ve talked plenty about brain-computer interfaces and novel computer chips that resemble the brain. We’ve covered how those “neuromorphic” chips could link up into tremendously powerful computing entities, using engineered communication nodes called artificial synapses.

As Moore’s law is dying, we even said that neuromorphic computing is one path towards the future of extremely powerful, low energy consumption artificial neural network-based computing—in hardware—that could in theory better link up with the brain. Because the chips “speak” the brain’s language, in theory they could become neuroprosthesis hubs far more advanced and “natural” than anything currently possible.

This month, an international team put all of those ingredients together, turning theory into reality.

The three labs, scattered across Padova, Italy, Zurich, Switzerland, and Southampton, England, collaborated to create a fully self-controlled, hybrid artificial-biological neural network that communicated using biological principles, but over the internet.

The three-neuron network, linked through artificial synapses that emulate the real thing, was able to reproduce a classic neuroscience experiment that’s considered the basis of learning and memory in the brain. In other words, artificial neuron and synapse “chips” have progressed to the point where they can actually use a biological neuron intermediary to form a circuit that, at least partially, behaves like the real thing.

That’s not to say cyborg brains are coming soon. The simulation only recreated a small network that supports excitatory transmission in the hippocampus—a critical region that supports memory—and most brain functions require enormous cross-talk between numerous neurons and circuits. Nevertheless, the study is a jaw-dropping demonstration of how far we’ve come in recreating biological neurons and synapses in artificial hardware.

And perhaps one day, the currently “experimental” neuromorphic hardware will be integrated into broken biological neural circuits as bridges to restore movement, memory, personality, and even a sense of self.

The Artificial Brain Boom
One important thing: this study relies heavily on a decade of research into neuromorphic computing, or the implementation of brain functions inside computer chips.

The best-known example is perhaps IBM’s TrueNorth, which leveraged the brain’s computational principles to build a completely different computer than what we have today. Today’s computers run on a von Neumann architecture, in which memory and processing modules are physically separate. In contrast, the brain’s computing and memory are simultaneously achieved at synapses, small “hubs” on individual neurons that talk to adjacent ones.

Because memory and processing occur on the same site, biological neurons don’t have to shuttle data back and forth between processing and storage compartments, massively reducing processing time and energy use. What’s more, a neuron’s history will also influence how it behaves in the future, increasing flexibility and adaptability compared to computers. With the rise of deep learning, which loosely mimics neural processing as the prima donna of AI, the need to reduce power while boosting speed and flexible learning is becoming ever more tantamount in the AI community.

Neuromorphic computing was partially born out of this need. Most chips utilize special ingredients that change their resistance (or other physical characteristics) to mimic how a neuron might adapt to stimulation. Some chips emulate a whole neuron, that is, how it responds to a history of stimulation—does it get easier or harder to fire? Others imitate synapses themselves, that is, how easily they will pass on the information to another neuron.

Although single neuromorphic chips have proven to be far more efficient and powerful than current computer chips running machine learning algorithms in toy problems, so far few people have tried putting the artificial components together with biological ones in the ultimate test.

That’s what this study did.

A Hybrid Network
Still with me? Let’s talk network.

It’s gonna sound complicated, but remember: learning is the formation of neural networks, and neurons that fire together wire together. To rephrase: when learning, neurons will spontaneously organize into networks so that future instances will re-trigger the entire network. To “wire” together, downstream neurons will become more responsive to their upstream neural partners, so that even a whisper will cause them to activate. In contrast, some types of stimulation will cause the downstream neuron to “chill out” so that only an upstream “shout” will trigger downstream activation.

Both these properties—easier or harder to activate downstream neurons—are essentially how the brain forms connections. The “amping up,” in neuroscience jargon, is long-term potentiation (LTP), whereas the down-tuning is LTD (long-term depression). These two phenomena were first discovered in the rodent hippocampus more than half a century ago, and ever since have been considered as the biological basis of how the brain learns and remembers, and implicated in neurological problems such as addition (seriously, you can’t pass Neuro 101 without learning about LTP and LTD!).

So it’s perhaps especially salient that one of the first artificial-brain hybrid networks recapitulated this classic result.

To visualize: the three-neuron network began in Switzerland, with an artificial neuron with the badass name of “silicon spiking neuron.” That neuron is linked to an artificial synapse, a “memristor” located in the UK, which is then linked to a biological rat neuron cultured in Italy. The rat neuron has a “smart” microelectrode, controlled by the artificial synapse, to stimulate it. This is the artificial-to-biological pathway.

Meanwhile, the rat neuron in Italy also has electrodes that listen in on its electrical signaling. This signaling is passed back to another artificial synapse in the UK, which is then used to control a second artificial neuron back in Switzerland. This is the biological-to-artificial pathway back. As a testimony in how far we’ve come in digitizing neural signaling, all of the biological neural responses are digitized and sent over the internet to control its far-out artificial partner.

Here’s the crux: to demonstrate a functional neural network, just having the biological neuron passively “pass on” electrical stimulation isn’t enough. It has to show the capacity to learn, that is, to be able to mimic the amping up and down-tuning that are LTP and LTD, respectively.

You’ve probably guessed the results: certain stimulation patterns to the first artificial neuron in Switzerland changed how the artificial synapse in the UK operated. This, in turn, changed the stimulation to the biological neuron, so that it either amped up or toned down depending on the input.

Similarly, the response of the biological neuron altered the second artificial synapse, which then controlled the output of the second artificial neuron. Altogether, the biological and artificial components seamlessly linked up, over thousands of miles, into a functional neural circuit.

Cyborg Mind-Meld
So…I’m still picking my jaw up off the floor.

It’s utterly insane seeing a classic neuroscience learning experiment repeated with an integrated network with artificial components. That said, a three-neuron network is far from the thousands of synapses (if not more) needed to truly re-establish a broken neural circuit in the hippocampus, which DARPA has been aiming to do. And LTP/LTD has come under fire recently as the de facto brain mechanism for learning, though so far they remain cemented as neuroscience dogma.

However, this is one of the few studies where you see fields coming together. As Richard Feynman famously said, “What I cannot recreate, I cannot understand.” Even though neuromorphic chips were built on a high-level rather than molecular-level understanding of how neurons work, the study shows that artificial versions can still synapse with their biological counterparts. We’re not just on the right path towards understanding the brain, we’re recreating it, in hardware—if just a little.

While the study doesn’t have immediate use cases, practically it does boost both the neuromorphic computing and neuroprosthetic fields.

“We are very excited with this new development,” said study author Dr. Themis Prodromakis at the University of Southampton. “On one side it sets the basis for a novel scenario that was never encountered during natural evolution, where biological and artificial neurons are linked together and communicate across global networks; laying the foundations for the Internet of Neuro-electronics. On the other hand, it brings new prospects to neuroprosthetic technologies, paving the way towards research into replacing dysfunctional parts of the brain with AI chips.”

Image Credit: Gerd Altmann from Pixabay Continue reading

Posted in Human Robots

#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

#436546 How AI Helped Predict the Coronavirus ...

Coronavirus has been all over the news for the last couple weeks. A dedicated hospital sprang up in just eight days, the stock market took a hit, Chinese New Year celebrations were spoiled, and travel restrictions are in effect.

But let’s rewind a bit; some crucial events took place before we got to this point.

A little under two weeks before the World Health Organization (WHO) alerted the public of the coronavirus outbreak, a Canadian artificial intelligence company was already sounding the alarm. BlueDot uses AI-powered algorithms to analyze information from a multitude of sources to identify disease outbreaks and forecast how they may spread. On December 31st 2019, the company sent out a warning to its customers to avoid Wuhan, where the virus originated. The WHO didn’t send out a similar public notice until January 9th, 2020.

The story of BlueDot’s early warning is the latest example of how AI can improve our identification of and response to new virus outbreaks.

Predictions Are Bad News
Global pandemic or relatively minor scare? The jury is still out on the coronavirus. However, the math points to signs that the worst is yet to come.

Scientists are still working to determine how infectious the virus is. Initial analysis suggests it may be somewhere between influenza and polio on the virus reproduction number scale, which indicates how many new cases one case leads to.

UK and US-based researchers have published a preliminary paper estimating that the confirmed infected people in Wuhan only represent five percent of those who are actually infected. If the models are correct, 190,000 people in Wuhan will be infected by now, major Chinese cities are on the cusp of large-scale outbreaks, and the virus will continue to spread to other countries.

Finding the Start
The spread of a given virus is partly linked to how long it remains undetected. Identifying a new virus is the first step towards mobilizing a response and, in time, creating a vaccine. Warning at-risk populations as quickly as possible also helps with limiting the spread.

These are among the reasons why BlueDot’s achievement is important in and of itself. Furthermore, it illustrates how AIs can sift through vast troves of data to identify ongoing virus outbreaks.

BlueDot uses natural language processing and machine learning to scour a variety of information sources, including chomping through 100,000 news reports in 65 languages a day. Data is compared with flight records to help predict virus outbreak patterns. Once the automated data sifting is completed, epidemiologists check that the findings make sense from a scientific standpoint, and reports are sent to BlueDot’s customers, which include governments, businesses, and public health organizations.

AI for Virus Detection and Prevention
Other companies, such as Metabiota, are also using data-driven approaches to track the spread of the likes of the coronavirus.

Researchers have trained neural networks to predict the spread of infectious diseases in real time. Others are using AI algorithms to identify how preventive measures can have the greatest effect. AI is also being used to create new drugs, which we may well see repeated for the coronavirus.

If the work of scientists Barbara Han and David Redding comes to fruition, AI and machine learning may even help us predict where virus outbreaks are likely to strike—before they do.

The Uncertainty Factor
One of AI’s core strengths when working on identifying and limiting the effects of virus outbreaks is its incredibly insistent nature. AIs never tire, can sift through enormous amounts of data, and identify possible correlations and causations that humans can’t.

However, there are limits to AI’s ability to both identify virus outbreaks and predict how they will spread. Perhaps the best-known example comes from the neighboring field of big data analytics. At its launch, Google Flu Trends was heralded as a great leap forward in relation to identifying and estimating the spread of the flu—until it underestimated the 2013 flu season by a whopping 140 percent and was quietly put to rest.

Poor data quality was identified as one of the main reasons Google Flu Trends failed. Unreliable or faulty data can wreak havoc on the prediction power of AIs.

In our increasingly interconnected world, tracking the movements of potentially infected individuals (by car, trains, buses, or planes) is just one vector surrounded by a lot of uncertainty.

The fact that BlueDot was able to correctly identify the coronavirus, in part due to its AI technology, illustrates that smart computer systems can be incredibly useful in helping us navigate these uncertainties.

Importantly, though, this isn’t the same as AI being at a point where it unerringly does so on its own—which is why BlueDot employs human experts to validate the AI’s findings.

Image Credit: Coronavirus molecular illustration, Gianluca Tomasello/Wikimedia Commons Continue reading

Posted in Human Robots