{"id":2241,"date":"2020-02-06T02:36:52","date_gmt":"2020-02-05T23:36:52","guid":{"rendered":"http:\/\/kusuaks7\/?p=1846"},"modified":"2024-01-17T11:21:44","modified_gmt":"2024-01-17T11:21:44","slug":"neuroscience-shows-whats-right-and-wrong-with-ai","status":"publish","type":"post","link":"https:\/\/www.experfy.com\/blog\/ai-ml\/neuroscience-shows-whats-right-and-wrong-with-ai\/","title":{"rendered":"Neuroscience shows what\u2019s right and wrong with AI"},"content":{"rendered":"\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tTwo separate studies, one by UK-based artificial intelligence lab DeepMind and the other by researchers in Germany and Greece, display the fascinating relations between AI and neuroscience.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\"\"\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

Image credit: Depositphotos<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t

\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tAs most scientists will tell you,\u00a0we are still decades away<\/a>\u00a0from building artificial general intelligence, machines that can solve problems as efficiently as humans. On the path to creating general AI, the human brain, arguably the most complex creation of nature, is the best guide we have.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tAdvances in neuroscience, the study of nervous systems, provide interesting insights into how the brain works, a key component for developing better AI systems. Reciprocally, the development of better AI systems can help drive neuroscience forward and further unlock the secrets of the brain.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tFor instance,\u00a0convolutional neural networks (CNN)<\/a>, one of the key contributors to recent advances in artificial intelligence, are largely inspired by neuroscience research on the visual cortex. On the other hand, neuroscientist leverage AI algorithms to\u00a0study millions of signals from the brain<\/a>\u00a0and find patterns that would have gone. The two fields are closely related and their synergies produce very interesting results.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tRecent discoveries in neuroscience show what we\u2019re doing right in AI, and what we\u2019ve got wrong.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

DeepMind\u2019s AI research shows connections between dopamine and reinforcement learning<\/h2><\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\"\"\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

Reinforcement learning is a hot area of AI research<\/p>\nA recent study by researchers at DeepMind prove that AI research (at least part of it) is headed in the right direction.\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t

\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tThanks to neuroscience, we know that one of the basic mechanisms through which humans and animals learn is rewards and punishments. Positive outcomes encourage us to repeat certain tasks (do sports, study for exams, etc.) while negative results detract us from repeating mistakes (touch a hot stove).\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tThe reward and punishment mechanism is best known by the experiments of Russian physiologist\u00a0Ivan Pavlov<\/a>, who trained dogs to expect food whenever they hear a bell. We also know that dopamine, a neurotransmitter chemical produced in the midbrain, plays a great role in regulating the reward functions of the brain.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tReinforcement learning<\/a>, one of the hottest areas of artificial intelligence research, has been roughly fashioned after the reward\/punishment mechanism of the brain. In RL, an AI agent is set to explore a problem space and try different actions. For each action it performs, the agent receives a numerical reward or penalty. Through massive trial and error and by examining the outcome of its actions, the AI agent develops a mathematical model optimized to maximize rewards and avoiding penalties. (In reality, it\u2019s a bit more complicated and involves dealing with exploration and exploitation and other challenges.)\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tMore recently, AI researchers have been focusing on distributional reinforcement learning to create better models. The basic idea behind distributional RL is to use multiple factors to predict rewards and punishments in a spectrum of optimistic and pessimistic ways. Distributional reinforcement learning has been pivotal in creating AI agents that are more resilient to changes in their environments.\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tThe new research, jointly done by Harvard University and DeepMind and published in\u00a0Nature<\/a>\u00a0<\/em>last week, has found properties in the brain of mice that are very similar to those of distributional reinforcement learning. The AI researchers measured dopamine firing rates in the brain to examine the variance in reward prediction rates of biological neurons.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tInterestingly, the same optimism and pessimism mechanism that AI scientists had programmed in distributional reinforcement learning models was found in the nervous system of mice. \u201cIn summary, we found that dopamine neurons in the brain were each tuned to different levels of pessimism or optimism,\u201d DeepMind\u2019s researchers wrote in a\u00a0blog post<\/a>\u00a0published on the AI lab\u2019s website. \u201cIn artificial reinforcement learning systems, this diverse tuning creates a richer training signal that greatly speeds learning in neural networks, and we speculate that the brain might use it for the same reason.\u201d\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tWhat makes this finding special is that while AI research usually takes inspiration from neuroscience discovery, in this case, neuroscience research has validated AI discoveries. \u201cIt gives us increased confidence that AI research is on the right track, since this algorithm is already being used in the most intelligent entity we\u2019re aware of: the brain,\u201d the researchers write.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tIt will also lay the groundwork for further research in neuroscience, which will, in turn, benefit the field of AI.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

Neurons are not as dumb as we think<\/h2><\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\"\"\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

Source: Flickr (Penn State<\/a>)<\/p>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t

\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tWhile DeepMind\u2019s new findings confirmed the work done in AI reinforcement learning research, another research by scientists in Berlin, this time\u00a0published in\u00a0Science<\/em><\/a>\u00a0in early January, proves that some of the fundamental assumptions we made about the brain are quite wrong.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\nThe general belief about the structure of the brain is that neurons, the basic component of the nervous system are simple integrators that calculate the weighted sum of their inputs.\u00a0Artificial neural networks<\/a>, a popular type of\u00a0machine learning<\/a>\u00a0algorithm, have been designed based on this belief.\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tAlone, an artificial neuron performs a very simple operation. It takes several inputs, multiplies them by predefined weights, sums them and runs them through an activation function. But when connecting thousands and millions (and billions) of artificial neurons in multiple layers, you obtain a very flexible mathematical function that can solve complex problems such as\u00a0detecting objects in images<\/a>\u00a0or transcribing speech.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\"\"\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

The structure of an artificial neuron, the basic component of artificial neural networks (source: Wikipedia)<\/p>\nMulti-layered networks of artificial neurons, generally called deep neural networks, are the main drive behind the\u00a0deep learning<\/a>\u00a0revolution in the past decade.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t

\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tBut the general perception of biological neurons being \u201cdumb\u201d calculators of basic math is overly simplistic. The recent findings of the German researchers, which were later corroborated by neuroscientists at a lab in Greece, proved that single neurons can perform XOR operations, a premise that was rejected by AI pioneers such as Marvin Minsky and Seymour Papert.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tWhile not all neurons have this capability, the implications of the finding are significant. For instance, it might mean that a single neuron might contain a deep network within itself. Konrad Kording, a computational neuroscientist at the University of Pennsylvania who was not involved in the research,\u00a0told\u00a0Quanta Magazine<\/em><\/a>\u00a0that the finding could mean \u201ca single neuron may be able to compute truly complex functions. For example, it might, by itself, be able to recognize an object.\u201d\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tWhat does this mean for artificial intelligence research? At the very least, it means that we need to rethink our modeling of neurons. It might spur research in new artificial neuron structures and networks with different types of neurons. Maybe it might help free us from the trap of having to build\u00a0extremely large neural networks and datasets<\/a>\u00a0to solve very simple problems.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\u201cThe whole game\u2014to come up with how you get smart cognition out of dumb neurons\u2014might be wrong,\u201d cognitive scientist Gary Marcus, who also spoke to\u00a0Quanta<\/em>, said in this regard.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<\/div>\n\t\t","protected":false},"excerpt":{"rendered":"

Advances in neuroscience, the study of nervous systems, provide interesting insights into how the brain works a key component for developing better AI systems. Reciprocally, the development of better AI systems can help drive neuroscience forward and further unlock the secrets of the brain. For instance, convolutional neural networks (CNN), one of the key contributors to recent advances in artificial intelligence, are largely inspired by neuroscience research on the visual cortex. Recent discoveries in neuroscience show what we’re doing right in AI, and what we’ve got wrong.<\/p>\n","protected":false},"author":109,"featured_media":3595,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"content-type":"","footnotes":""},"categories":[183],"tags":[97],"ppma_author":[1946],"class_list":["post-2241","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ai-ml","tag-artificial-intelligence"],"authors":[{"term_id":1946,"user_id":109,"is_guest":0,"slug":"ben-dickson","display_name":"Ben Dickson","avatar_url":"https:\/\/www.experfy.com\/blog\/wp-content\/uploads\/2020\/04\/medium_8aaf6bea-c4c1-455f-8156-8007d70910f8-150x150.jpg","user_url":"https:\/\/bdtechtalks.com\/","last_name":"Dickson","first_name":"Ben","job_title":"","description":"Ben Dickson is an experienced software engineer and tech blogger. He contributes regularly to major tech websites such as the Next Web, the Daily Dot, PCMag.com, Cointelegraph, VentureBeat, International Business Times UK, and The Huffington Post."}],"_links":{"self":[{"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/posts\/2241","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/users\/109"}],"replies":[{"embeddable":true,"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/comments?post=2241"}],"version-history":[{"count":5,"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/posts\/2241\/revisions"}],"predecessor-version":[{"id":35524,"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/posts\/2241\/revisions\/35524"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/media\/3595"}],"wp:attachment":[{"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/media?parent=2241"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/categories?post=2241"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/tags?post=2241"},{"taxonomy":"author","embeddable":true,"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/ppma_author?post=2241"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}