
Economic Attention Networks:Associative Memory and Resource Allocation for General Intelligence
4 months ago
Economic Attention Networks: Associative Memory and Resource Allocation for General Intelligence
A presentation on a paper by Matthew Ikle, Joel Pitt, Ben Goertzel, George Sellman
A novel method for simultaneously storing memories and allocating resources in AI systems is presented. The method, Economic Attention Networks (ECANs), bears some resemblance to the spread of activation in attractor neural networks, but differs via explicitly differentiating two kinds of “activation” (Short Term Importance, related to processor allocation; and Long Term Importance, related to memory allocation), and in using equations that are based on ideas from economics rather than approximative neural modeling. Here we explain the basic ideas of ECANs, and then investigate the functionality of ECANs as associative memories, via mathematical analysis and the reportage of experimental results obtained from the implementation of ECANs in the OpenCog integrative AGI system.
A presentation on a paper by Matthew Ikle, Joel Pitt, Ben Goertzel, George Sellman
A novel method for simultaneously storing memories and allocating resources in AI systems is presented. The method, Economic Attention Networks (ECANs), bears some resemblance to the spread of activation in attractor neural networks, but differs via explicitly differentiating two kinds of “activation” (Short Term Importance, related to processor allocation; and Long Term Importance, related to memory allocation), and in using equations that are based on ideas from economics rather than approximative neural modeling. Here we explain the basic ideas of ECANs, and then investigate the functionality of ECANs as associative memories, via mathematical analysis and the reportage of experimental results obtained from the implementation of ECANs in the OpenCog integrative AGI system.
-
Steve Nordquist 4 months agoI'm still programming angst and wondering how Wolfram keeps such an even keel, and it turns out you're working out fun things to do with search (associative memory) silicon once luck times out. Thank you for going to AGI and manually compensating for the reeling, pitching floor. (And giving Sedjnowski's old neural modeling a break. Poor guy barely got 8 years of Science edited, and I recently saw it listed as a tabloid (by paleontologists (Hey, how are your grandchildrens' skeletons? etc.), though.))
This conversation is missing your voice. Take five seconds to join Vimeo or log in.
-
Vimeo: About / Blog / Developers / Jobs / Community Guidelines / Community Forums / Help Center / Site Map / Merchandise
/ Get Vimeo

Previous Week