Accelerating Future Transhumanism, AI, nanotech, the Singularity, and extinction risk.


Josh Tenenbaum Video Again: Bayesian Models of Human Inductive Learning

I posted this only a month ago, but here's the link to the video again. People sometimes say there's been no progress in AI, but the kind of results obtained by Tenenbaum are amazing and open up a whole approach to AI that uses fast and frugal heuristics for reasoning and requires very minimal inspiration from the human brain.


In everyday learning and reasoning, people routinely draw successful generalizations from very limited evidence. Even young children can infer the meanings of words, hidden properties of objects, or the existence of causal relations from just one or a few relevant observations -- far outstripping the capabilities of conventional learning machines. How do they do it? And how can we bring machines closer to these human-like learning abilities? I will argue that people's everyday inductive leaps can be understood as approximations to Bayesian computations operating over structured representations of the world, what cognitive scientists have called "intuitive theories" or "schemas". For each of several everyday learning tasks, I will consider how appropriate knowledge representations are structured and used, and how these representations could themselves be learned via Bayesian methods. The key challenge is to balance the need for strongly constrained inductive biases -- critical for generalization from very few examples -- with the flexibility to learn about the structure of new domains, to learn new inductive biases suitable for environments which we could not have been pre-programmed to perform in. The models I discuss will connect to several directions in contemporary machine learning, such as semi-supervised learning, structure learning in graphical models, hierarchical Bayesian modeling, and nonparametric Bayes.

Filed under: AI, science, videos Leave a comment
Comments (4) Trackbacks (0)
  1. Are we going to replace “gut feelings” with probabilities? Seems like that sort of thing is more likely to create malevolent AIs than copying cat brains. At least cats are nice sometimes.

  2. Rylee luvs u alex your popular i actually wish i actually wasnt 11 thus could particular date you plus i actually need i new you

  3. Thank you a lot for providing individuals with an extremely brilliant possiblity to read articles and blog posts from this site. It is always very ideal and also stuffed with fun for me and my office co-workers to visit your site at a minimum three times a week to find out the latest things you will have. And lastly, I am also always amazed with the great tricks you serve. Some 4 points in this post are undeniably the simplest I’ve ever had.

  4. how to get over a break up yahoo answers

Leave a comment

No trackbacks yet.