computational models

computational models - Ricardo Rodriguez Cog Neuro Article...

Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon
Ricardo Rodriguez Cog Neuro Article Sumary – Rueckl et. Al. A Computational Model of “What” and “Where” in Visual Systems The primate visual cortex is a powerful tool for navigating complex physical environments. For every visible stimulus, it simultaneously computes location and identity with impressive success and speed. Anatomical studies of visual cortices in human and non-human primate brains have shown that the calculations for “where” and “what” data reside in different neurophysiological loci – the dorsal (mostly parietal lobe) and ventral (temporal lobe) streams, respectively. This physical implementation of a split-processing model, assumedly a feature evolved for its efficiency and accuracy, begs the computational question – how are split-processing models better than unsplit ones? A study done by Rueckl et. al. demonstrated how a simple 3-layer system based on the connectionist paradigm (suggested to be a major feature of neural networks) could, over several trials, learn how to identify and locate simple objects on a 5x5 grid with surprising precision. More importantly, the experimenters showed how a split-processing
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 2
This is the end of the preview. Sign up to access the rest of the document.

Page1 / 3

computational models - Ricardo Rodriguez Cog Neuro Article...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online