News for hackers. Stuff that matters.
Re:One-shot Learning with Memory-Augmented Neural Networks by SubiculumCode on Friday May 20, 2016 @07:33PM (#11742357)
I study the neuroscience of episodic memory. Episodic memory requires one shot learning critically dependent on the hippocampus which is posited to use operations of pattern separation (to reduce intereference for distinct memories with similar features) and completion ( retrieve whole from partial input of features) to encode and retrieve bound representations, respectively. Prior to the hippocampus are operations that detect feature novelty in the perirhinal cortex. In contrast to these functions is the slow learning of the neocortex which supports semantic memory. Episodic and semantic memory funcions are intertwined in a complex way.

Seems to my mind that deep learning is the cortex, and the binding function is the hippocampus. Add some executive control functions to guide learning strategically and it will start sounding eery.

Re:One-shot Learning with Memory-Augmented Neural Networks by rybosome on Friday May 20, 2016 @09:22PM (#11742702)
It seems like the binding function (e.g. the hippocampus) is the next major challenge. I think this is related to what is referred to as "transfer learning", where the training a model has received in one domain can be partially applied to a new domain such that training time is reduced; in particular, "retriev(ing) whole from partial input of features" reads to me as exactly the missing link that would allow transfer learning to take place. If memory-augmented neural networks put us down that path, then I'd wager that executive control functions are less complex (at least to fake passably)...we could be in for some interesting times.
Re:One-shot Learning with Memory-Augmented Neural Networks by justinclift on Friday May 20, 2016 @07:46PM (#11742418)
Hook that up to a rat and see what happens?

[5 months later]

We welcome our new AI-Rat overlords? ;)