{"id":1417,"date":"2011-01-09T00:00:16","date_gmt":"2011-01-09T04:00:16","guid":{"rendered":"http:\/\/www.synapse9.com\/signals\/?p=1417"},"modified":"2011-01-09T00:00:16","modified_gmt":"2011-01-09T04:00:16","slug":"the-limits-of-learning-machines-drawing-a-blank","status":"publish","type":"post","link":"https:\/\/synapse9.com\/signals\/the-limits-of-learning-machines-drawing-a-blank\/","title":{"rendered":"The limits of learning machines\u2026 (drawing a blank!)"},"content":{"rendered":"

One of the constant threads of my work from the start has been the curious gaps between the world our minds present to us as a whole, and the one nature builds for us to\u00a0*work*<\/strong> as a whole (using a considerably more complete deck of cards, you might say)\u2026\u00a0\";-)\"Here\u2019s a good note to a mathematician and physicist, John Baez on his Azimuth website, prompted by the interest he expressed in studying the math of real world problems in his\u00a0comments regarding mathematical economics<\/a>.<\/p><\/blockquote>\n

John, in your first comment at the top I noticed your intent to go back to teaching math differently next time, as you said:<\/p>\n

\u201cbut now I\u2019m more keen on real-world examples that illustrate the big problems facing our civilization..\u201d<\/h3>\n

What could be challenging and intriguing is to try to model the elemental problem of \u201ccomplex systems with thinking parts\u201d, or “learning systems”.<\/p>\n

The problem is how a network of independently \u201cobserving, interpreting & responding\u201d agents would interact. \u00a0 They are not follow rules, exactly, but following discoveries instead.<\/p>\n

Learning systems share their own original learning and responses and developed a combined viewpoint of their dynamically changing environment. \u00a0Economic markets do that for example.<\/p>\n

Their \u201cthinking nodes\u201d are key working parts in all kinds of natural system economies, responsible for swarm behaviors in nature generally, and not just in human economies. Whether their connections are direct through open markets or through specialized groups (like this blog, say), the interesting ways nature uses that structure to get distributed systems to work as rapidly reorganizing whole systems is a big part of the fascination. To avoid some of the indeterminacy of it all one starting point is to focus on the natural limitations of the actors or their environment, i.e. response time limits.<\/p>\n

It would be interesting to model conditions in which smooth flowing learning and communication becomes turbulent, for example. That happens easily when the delay or difficulty in observation leads to interpretation uncertainty, and in turn leads to response errors like indecision or panic etc\u2026 See my idea? Maybe if people learn to play with idealized examples of this kind of thing it would give them a leg up for learning how to observe active learning system behaviors in real time they\u2019d otherwise not think twice about.<\/p>\n

There was a great example of an emerging systemic distortion developing in the collective \u201cthinking system\u201d of the financial markets in 2007, displayed in the S&P 500 index, that kind of points to the subject. This is just one of a wide variety of other kinds and scales of emergent learning system behaviors, growth itself being both the simplest, most common and most difficult to understand.<\/p>\n

\"S&P
\nThe screen shot shows the six month period from March to August, displaying increasing \u201cfishtailing\u201d leading to turbulence and the S&P whole market plunge, that triggered global intervention. I found lots of people who indeed agreed they\u2019d never seen anything systemic like this, and that a functioning market should never produce them. I think what was driving it was that at that time people in the financial markets were racing all over looking for where to hide their money\u2026 they were panicking.<\/p>\n

Another part of what\u2019s interesting about it is how a highly exceptional systemic behavior did not stimulate the curiosity of the economists or traders I could find. All I could get was an opinion that it didn\u2019t look right. That \u201cfailure of curiosity\u201d hints at the deeper problem, of course.<\/p>\n

That time the intervention by the market system regulators was able to save the day. That was not the case the next time \u201call hell broke loose\u201d, though.<\/p>\n

That people \u201cin the know\u201d didn\u2019t take interest in the problem, of course, is another problem when relying on the \u201cobserving, interpreting & responding\u201d of independent agents. They can look at something unfamiliar and \u201cdraw a blank\u201d.<\/p>\n

Anyway, that might help suggest the general lines of research into such emergent phenomena I\u2019m trying to suggest. Various pieces of it could be experimented with mathematically, and give people an idea of what to be curious about, and \u201cif you see something say something\u201d if they happen to notice them taking place.<\/p>\n

Phil<\/p>\n

p.s.
\nI don\u2019t know how to do the math, really, but you might. What I was suggesting in my comment yesterday on your interest in real world problems for Mathematical Economics is a form of modeling for economic systems somewhat like QM.<\/p>\n

The difference from QM for studying the boundary conditions for large \u201cobservation, interpretation & response\u201d networks (that economies are built around) would be in the modeling of the \u201cmysterious hidden process\u201d connecting the \u201cbefore\u201d and \u201cafter\u201d states. For learning machines that process would have variable non-zero duration as well as uncertainty (in this case for altogether human rather than mathematical reasons).<\/p>\n

That would let you explore some of the natural limitations of using such an operating system to run a planet. These kinds of structures proliferate in economies and other natural systems, especially those that exhibit rapid organizational development processes. So the work would be both innovative and possibly quite valuable.<\/p>\n

 <\/p>\n","protected":false},"excerpt":{"rendered":"

One of the constant threads of my work from the start has been the curious gaps between the world our minds present to us as a whole, and the one nature builds for us to\u00a0*work* as a whole (using a considerably more complete deck of cards, you might say)\u2026\u00a0Here\u2019s a good note to a mathematician … Continue reading The limits of learning machines\u2026 (drawing a blank!)<\/span> →<\/span><\/a><\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_crdt_document":"","footnotes":""},"categories":[4,6,8],"tags":[],"class_list":["post-1417","post","type-post","status-publish","format-standard","hentry","category-teaching","category-mail","category-theory"],"_links":{"self":[{"href":"https:\/\/synapse9.com\/signals\/wp-json\/wp\/v2\/posts\/1417","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/synapse9.com\/signals\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/synapse9.com\/signals\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/synapse9.com\/signals\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/synapse9.com\/signals\/wp-json\/wp\/v2\/comments?post=1417"}],"version-history":[{"count":0,"href":"https:\/\/synapse9.com\/signals\/wp-json\/wp\/v2\/posts\/1417\/revisions"}],"wp:attachment":[{"href":"https:\/\/synapse9.com\/signals\/wp-json\/wp\/v2\/media?parent=1417"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/synapse9.com\/signals\/wp-json\/wp\/v2\/categories?post=1417"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/synapse9.com\/signals\/wp-json\/wp\/v2\/tags?post=1417"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}