{"id":10638,"date":"2022-03-19T18:00:32","date_gmt":"2022-03-19T18:00:32","guid":{"rendered":"http:\/\/TheNextWeb=1382807"},"modified":"2022-03-19T18:00:32","modified_gmt":"2022-03-19T18:00:32","slug":"neuro-symbolic-ai-brings-us-closer-to-machines-with-common-sense","status":"publish","type":"post","link":"https:\/\/www.londonchiropracter.com\/?p=10638","title":{"rendered":"Neuro-symbolic AI brings us closer to machines with common sense"},"content":{"rendered":"\n

This article is part of our coverage of the latest in AI research<\/a>.<\/em><\/p>\n

Artificial intelligence research has made great achievements in solving specific applications, but we\u2019re still far from the kind of general-purpose AI systems<\/a> that scientists have been dreaming of for decades.<\/p>\n

Among the solutions being explored to overcome the barriers of AI is the idea of neuro-symbolic systems<\/a> that bring together the best of different branches of computer science. In a talk<\/a> at the IBM Neuro-Symbolic AI Workshop, Joshua Tenenbaum, professor of computational cognitive science at the Massachusetts Institute of Technology, explained how neuro-symbolic systems can help to address some of the key problems of current AI systems.<\/p>\n

Among the many gaps in AI, Tenenbaum is focused on one in particular: \u201cHow do we go beyond the idea of intelligence as recognizing patterns in data and approximating functions and more toward the idea of all the things the human mind does when you\u2019re modeling the world, explaining and understanding the things you\u2019re seeing, imagining things that you can\u2019t see but could happen, and making them into goals that you can achieve by planning actions and solving problems?\u201d<\/p>\n

Admittedly, that is a big gap, but bridging it starts with exploring one of the fundamental aspects of intelligence that humans and many animals share: intuitive physics and psychology.<\/p>\n

Intuitive physics and psychology<\/h2>\n

Our minds are built not just to see patterns in pixels and soundwaves but to understand the world through models<\/a>. As humans, we start developing these models as early as three months of age, by observing and acting in the world.<\/p>\n

We break down the world into objects and agents, and interactions between these objects and agents. Agents have their own goals and their own models of the world (which might be different from ours).<\/p>\n

For example, multiple studies<\/a> by researchers Felix Warneken and Michael Tomasello show that children develop abstract ideas about the physical world and other people and apply them in novel situations. For example, in the following video, through observation alone, the child realizes that the person holding the objects has a goal in mind and needs help with opening the door to the closet.<\/p>\n

These capabilities are often referred to as \u201cintuitive physics\u201d and \u201cintuitive psychology\u201d<\/a> or \u201ctheory of mind,\u201d and they are at the heart of common sense.<\/p>\n

\u201cThese systems develop quite early in the brain architecture that is to some extent shared with other species,\u201d Tenenbaum says. These cognitive systems are the bridge between all the other parts of intelligence such as the targets of perception, the substrate of action-planning, reasoning, and even language.<\/p>\n

AI agents should be able to reason and plan their actions based on mental representations they develop of the world and other agents through intuitive physics and theory of mind.<\/p>\n

Neuro-symbolic architecture<\/h2>\n

\"machine-learning-causality\"