Tag Archives: memory
A few years back, DeepMind’s Demis Hassabis famously prophesized that AI and neuroscience will positively feed into each other in a “virtuous circle.” If realized, this would fundamentally expand our insight into intelligence, both machine and human.
We’ve already seen some proofs of concept, at least in the brain-to-AI direction. For example, memory replay, a biological mechanism that fortifies our memories during sleep, also boosted AI learning when abstractly appropriated into deep learning models. Reinforcement learning, loosely based on our motivation circuits, is now behind some of AI’s most powerful tools.
Hassabis is about to be proven right again.
Last week, two studies independently tapped into the power of ANNs to solve a 70-year-old neuroscience mystery: how does our visual system perceive reality?
The first, published in Cell, used generative networks to evolve DeepDream-like images that hyper-activate complex visual neurons in monkeys. These machine artworks are pure nightmare fuel to the human eye; but together, they revealed a fundamental “visual hieroglyph” that may form a basic rule for how we piece together visual stimuli to process sight into perception.
In the second study, a team used a deep ANN model—one thought to mimic biological vision—to synthesize new patterns tailored to control certain networks of visual neurons in the monkey brain. When directly shown to monkeys, the team found that the machine-generated artworks could reliably activate predicted populations of neurons. Future improved ANN models could allow even better control, giving neuroscientists a powerful noninvasive tool to study the brain. The work was published in Science.
The individual results, though fascinating, aren’t necessarily the point. Rather, they illustrate how scientists are now striving to complete the virtuous circle: tapping AI to probe natural intelligence. Vision is only the beginning—the tools can potentially be expanded into other sensory domains. And the more we understand about natural brains, the better we can engineer artificial ones.
It’s a “great example of leveraging artificial intelligence to study organic intelligence,” commented Dr. Roman Sandler at Kernel.co on Twitter.
ANNs and biological vision have quite the history.
In the late 1950s, the legendary neuroscientist duo David Hubel and Torsten Wiesel became some of the first to use mathematical equations to understand how neurons in the brain work together.
In a series of experiments—many using cats—the team carefully dissected the structure and function of the visual cortex. Using myriads of images, they revealed that vision is processed in a hierarchy: neurons in “earlier” brain regions, those closer to the eyes, tend to activate when they “see” simple patterns such as lines. As we move deeper into the brain, from the early V1 to a nub located slightly behind our ears, the IT cortex, neurons increasingly respond to more complex or abstract patterns, including faces, animals, and objects. The discovery led some scientists to call certain IT neurons “Jennifer Aniston cells,” which fire in response to pictures of the actress regardless of lighting, angle, or haircut. That is, IT neurons somehow extract visual information into the “gist” of things.
That’s not trivial. The complex neural connections that lead to increasing abstraction of what we see into what we think we see—what we perceive—is a central question in machine vision: how can we teach machines to transform numbers encoding stimuli into dots, lines, and angles that eventually form “perceptions” and “gists”? The answer could transform self-driving cars, facial recognition, and other computer vision applications as they learn to better generalize.
Hubel and Wiesel’s Nobel-prize-winning studies heavily influenced the birth of ANNs and deep learning. Much of earlier ANN “feed-forward” model structures are based on our visual system; even today, the idea of increasing layers of abstraction—for perception or reasoning—guide computer scientists to build AI that can better generalize. The early romance between vision and deep learning is perhaps the bond that kicked off our current AI revolution.
It only seems fair that AI would feed back into vision neuroscience.
Hieroglyphs and Controllers
In the Cell study, a team led by Dr. Margaret Livingstone at Harvard Medical School tapped into generative networks to unravel IT neurons’ complex visual alphabet.
Scientists have long known that neurons in earlier visual regions (V1) tend to fire in response to “grating patches” oriented in certain ways. Using a limited set of these patches like letters, V1 neurons can “express a visual sentence” and represent any image, said Dr. Arash Afraz at the National Institute of Health, who was not involved in the study.
But how IT neurons operate remained a mystery. Here, the team used a combination of genetic algorithms and deep generative networks to “evolve” computer art for every studied neuron. In seven monkeys, the team implanted electrodes into various parts of the visual IT region so that they could monitor the activity of a single neuron.
The team showed each monkey an initial set of 40 images. They then picked the top 10 images that stimulated the highest neural activity, and married them to 30 new images to “evolve” the next generation of images. After 250 generations, the technique, XDREAM, generated a slew of images that mashed up contorted face-like shapes with lines, gratings, and abstract shapes.
This image shows the evolution of an optimum image for stimulating a visual neuron in a monkey. Image Credit: Ponce, Xiao, and Schade et al. – Cell.
“The evolved images look quite counter-intuitive,” explained Afraz. Some clearly show detailed structures that resemble natural images, while others show complex structures that can’t be characterized by our puny human brains.
This figure shows natural images (right) and images evolved by neurons in the inferotemporal cortex of a monkey (left). Image Credit: Ponce, Xiao, and Schade et al. – Cell.
“What started to emerge during each experiment were pictures that were reminiscent of shapes in the world but were not actual objects in the world,” said study author Carlos Ponce. “We were seeing something that was more like the language cells use with each other.”
This image was evolved by a neuron in the inferotemporal cortex of a monkey using AI. Image Credit: Ponce, Xiao, and Schade et al. – Cell.
Although IT neurons don’t seem to use a simple letter alphabet, it does rely on a vast array of characters like hieroglyphs or Chinese characters, “each loaded with more information,” said Afraz.
The adaptive nature of XDREAM turns it into a powerful tool to probe the inner workings of our brains—particularly for revealing discrepancies between biology and models.
The Science study, led by Dr. James DiCarlo at MIT, takes a similar approach. Using ANNs to generate new patterns and images, the team was able to selectively predict and independently control neuron populations in a high-level visual region called V4.
“So far, what has been done with these models is predicting what the neural responses would be to other stimuli that they have not seen before,” said study author Dr. Pouya Bashivan. “The main difference here is that we are going one step further and using the models to drive the neurons into desired states.”
It suggests that our current ANN models for visual computation “implicitly capture a great deal of visual knowledge” which we can’t really describe, but which the brain uses to turn vision information into perception, the authors said. By testing AI-generated images on biological vision, however, the team concluded that today’s ANNs have a degree of understanding and generalization. The results could potentially help engineer even more accurate ANN models of biological vision, which in turn could feed back into machine vision.
“One thing is clear already: Improved ANN models … have led to control of a high-level neural population that was previously out of reach,” the authors said. “The results presented here have likely only scratched the surface of what is possible with such implemented characterizations of the brain’s neural networks.”
To Afraz, the power of AI here is to find cracks in human perception—both our computational models of sensory processes, as well as our evolved biological software itself. AI can be used “as a perfect adversarial tool to discover design cracks” of IT, said Afraz, such as finding computer art that “fools” a neuron into thinking the object is something else.
“As artificial intelligence researchers develop models that work as well as the brain does—or even better—we will still need to understand which networks are more likely to behave safely and further human goals,” said Ponce. “More efficient AI can be grounded by knowledge of how the brain works.”
Image Credit: Sangoiri / Shutterstock.com Continue reading
2018 was bonkers for science.
From a woman who gave birth using a transplanted uterus, to the infamous CRISPR baby scandal, to forensics adopting consumer-based genealogy test kits to track down criminals, last year was a factory churning out scientific “whoa” stories with consequences for years to come.
With CRISPR still in the headlines, Britain ready to bid Europe au revoir, and multiple scientific endeavors taking off, 2019 is shaping up to be just as tumultuous.
Here are the science and health stories that may blow up in the new year. But first, a note of caveat: predicting the future is tough. Forecasting is the lovechild between statistics and (a good deal of) intuition, and entire disciplines have been dedicated to the endeavor. But January is the perfect time to gaze into the crystal ball for wisps of insight into the year to come. Last year we predicted the widespread approval of gene therapy products—on the most part, we nailed it. This year we’re hedging our bets with multiple predictions.
Gene Drives Used in the Wild
The concept of gene drives scares many, for good reason. Gene drives are a step up in severity (and consequences) from CRISPR and other gene-editing tools. Even with germline editing, in which the sperm, egg, or embryos are altered, gene editing affects just one genetic line—one family—at least at the beginning, before they reproduce with the general population.
Gene drives, on the other hand, have the power to wipe out entire species.
In a nutshell, they’re little bits of DNA code that help a gene transfer from parent to child with almost 100 percent perfect probability. The “half of your DNA comes from dad, the other comes from mom” dogma? Gene drives smash that to bits.
In other words, the only time one would consider using a gene drive is to change the genetic makeup of an entire population. It sounds like the plot of a supervillain movie, but scientists have been toying around with the idea of deploying the technology—first in mosquitoes, then (potentially) in rodents.
By releasing just a handful of mutant mosquitoes that carry gene drives for infertility, for example, scientists could potentially wipe out entire populations that carry infectious scourges like malaria, dengue, or Zika. The technology is so potent—and dangerous—the US Defense Advances Research Projects Agency is shelling out $65 million to suss out how to deploy, control, counter, or even reverse the effects of tampering with ecology.
Last year, the U.N. gave a cautious go-ahead for the technology to be deployed in the wild in limited terms. Now, the first release of a genetically modified mosquito is set for testing in Burkina Faso in Africa—the first-ever field experiment involving gene drives.
The experiment will only release mosquitoes in the Anopheles genus, which are the main culprits transferring disease. As a first step, over 10,000 male mosquitoes are set for release into the wild. These dudes are genetically sterile but do not cause infertility, and will help scientists examine how they survive and disperse as a preparation for deploying gene-drive-carrying mosquitoes.
Hot on the project’s heels, the nonprofit consortium Target Malaria, backed by the Bill and Melinda Gates foundation, is engineering a gene drive called Mosq that will spread infertility across the population or kill out all female insects. Their attempt to hack the rules of inheritance—and save millions in the process—is slated for 2024.
A Universal Flu Vaccine
People often brush off flu as a mere annoyance, but the infection kills hundreds of thousands each year based on the CDC’s statistical estimates.
The flu virus is actually as difficult of a nemesis as HIV—it mutates at an extremely rapid rate, making effective vaccines almost impossible to engineer on time. Scientists currently use data to forecast the strains that will likely explode into an epidemic and urge the public to vaccinate against those predictions. That’s partly why, on average, flu vaccines only have a success rate of roughly 50 percent—not much better than a coin toss.
Tired of relying on educated guesses, scientists have been chipping away at a universal flu vaccine that targets all strains—perhaps even those we haven’t yet identified. Often referred to as the “holy grail” in epidemiology, these vaccines try to alert our immune systems to parts of a flu virus that are least variable from strain to strain.
Last November, a first universal flu vaccine developed by BiondVax entered Phase 3 clinical trials, which means it’s already been proven safe and effective in a small numbers and is now being tested in a broader population. The vaccine doesn’t rely on dead viruses, which is a common technique. Rather, it uses a small chain of amino acids—the chemical components that make up proteins—to stimulate the immune system into high alert.
With the government pouring $160 million into the research and several other universal candidates entering clinical trials, universal flu vaccines may finally experience a breakthrough this year.
In-Body Gene Editing Shows Further Promise
CRISPR and other gene editing tools headed the news last year, including both downers suggesting we already have immunity to the technology and hopeful news of it getting ready for treating inherited muscle-wasting diseases.
But what wasn’t widely broadcasted was the in-body gene editing experiments that have been rolling out with gusto. Last September, Sangamo Therapeutics in Richmond, California revealed that they had injected gene-editing enzymes into a patient in an effort to correct a genetic deficit that prevents him from breaking down complex sugars.
The effort is markedly different than the better-known CAR-T therapy, which extracts cells from the body for genetic engineering before returning them to the hosts. Rather, Sangamo’s treatment directly injects viruses carrying the edited genes into the body. So far, the procedure looks to be safe, though at the time of reporting it was too early to determine effectiveness.
This year the company hopes to finally answer whether it really worked.
If successful, it means that devastating genetic disorders could potentially be treated with just a few injections. With a gamut of new and more precise CRISPR and other gene-editing tools in the works, the list of treatable inherited diseases is likely to grow. And with the CRISPR baby scandal potentially dampening efforts at germline editing via regulations, in-body gene editing will likely receive more attention if Sangamo’s results return positive.
Neuralink and Other Brain-Machine Interfaces
Neuralink is the stuff of sci fi: tiny implanted particles into the brain could link up your biological wetware with silicon hardware and the internet.
But that’s exactly what Elon Musk’s company, founded in 2016, seeks to develop: brain-machine interfaces that could tinker with your neural circuits in an effort to treat diseases or even enhance your abilities.
Last November, Musk broke his silence on the secretive company, suggesting that he may announce something “interesting” in a few months, that’s “better than anyone thinks is possible.”
Musk’s aspiration for achieving symbiosis with artificial intelligence isn’t the driving force for all brain-machine interfaces (BMIs). In the clinics, the main push is to rehabilitate patients—those who suffer from paralysis, memory loss, or other nerve damage.
2019 may be the year that BMIs and neuromodulators cut the cord in the clinics. These devices may finally work autonomously within a malfunctioning brain, applying electrical stimulation only when necessary to reduce side effects without requiring external monitoring. Or they could allow scientists to control brains with light without needing bulky optical fibers.
Cutting the cord is just the first step to fine-tuning neurological treatments—or enhancements—to the tune of your own brain, and 2019 will keep on bringing the music.
Image Credit: angellodeco / Shutterstock.com Continue reading