Tag Info

I think that your intuition about the lower "energy ratio" of spurious states explaining their greater susceptibility to unlearning might be correct. In a Hopfield Network spurious states are activity patterns that have not been explicitly embedded in the synaptic matrix, but are nonetheless stable. They are in other words "unwanted" attractor states that, ...

Evolution does not help Minsky's theory of a resourceful mind. Although he tries to frame his discussion in loose evolutionary terms in the Emotion Machine and the book it is based on: Society of Mind (here is a good review/summary). As you noted during your reading: Minsky backs himself up by saying "evolution did so", but hasn't provided tests or ...

I wonder if any of the work using Act-R would be relevant. See these Act-R publications with accompanying PDFs on visual search spatial reasoning and navigation (apologies if they're not relevant, this is outside my comfort zone)

I'm not sure I fully understand your design; perhaps you can clarify what you want your network to learn, why TD-learning "isn't cutting it", and what you mean by 'reinforcement' and 'prediction' learning. In particular, TD-learning is a reinforcement learning model, and it does reward based on predicted (and not just observed) outcomes. However, you seem ...

Consider that elimination of such a phenomena is not ideal. It's been proposed that actual neuronal networks exist under the tension of synchronous decoupling. http://www.sciencedirect.com/science/article/pii/S0896627308001281 To answer your question though, you probably should consider that reciprocal connections might not be between two individual ...

For what it's worth, I did a lot of research and did not find a solution. So I created my own using HTML, jQuery and a canvas. It's not pretty, but it does not require a lot of work because the functionality is simple: When you click on a node, display its edges and the associated weights.

If you are looking for a 'brain model of visual navigation', you just have to google it! You will find a whole Ph.D. thesis that exactly covers all what you are asking for: Learning Objects Places and Relation in a Brain Model of Visual Navigation. http://books.google.com/books/about/Learning_Objects_Places_and_Relations_in.html?id=yJo2twAACAAJ That ...