Show Tag: hierarchical-organization

Select Other Tags

Miikulainen et al. use a hierarchical version of their SOM-based algorithm to model natural development of visual capabilities.

The number of neurons in the lower stages of the visual processing hierarchy (V1) is much lower than in the higher stages (IT).

Selfridge's Pandemonium is (at least one) progenitor of all hierarchical cognitive architectures. It comprises a hierarchy of layers in which each layer detects patterns in the activity of its more primitive preceding layer.

Early work on layered architectures pre-wired all but the top-most layer and learned that.

Hinton states that in using SVMs, the actual features (of an image, article...) are extracted by some hand-crafted algorithm and only discriminating objects based on these features is learned.

He sees this as a modern version of what he calls a strategy of denial to learning feature extractors and hidden units.

Unsupervised learning extracts regularities in the input. Detected regularities can then be used for actual discrimination. Or unsupervised learning can be used again to detect regularities in these regularities.

The restricted Boltzman machine is an unsupervised learning algorithm which is similar to the wake-sleep algorithm. It uses stochastic learning, ie. neural activations are stochastic with continuous probabilities given by weights.

The visual cortex is hierarchically organized.

It seems a bit unclear to me what determines the hierarchy of the visual cortex if backward connections are predominant.

The temporal binding theory does not rely on a hierarchical architecture.

Neurons at low stages in the hierarchy of visual processing extract simple, localized features.

Hierarchical architectures for information processing have the benefit of being able to re-use processing primitives for different purposes.

There are shortcuts between the levels of visual processing in the visual cortex.

Pulvinar neurons seem to receive input and project to different layers in visual cortex:

They receive input from layer 5 and project to layers one and three.

Connectivity between pulvinar and MT is similar to connectivity between pulvinar and visual cortex.

Early visual neurons (eg. in V1) do not seem to encode probabilities.

Many recent neural theories assume that higher-level brain regions form hypotheses about the world and that top-down, or feedback connections carry predictions for low-level stimuli derived from these hypotheses.

Early theories which assume that higher-level brain regions form hypotheses about the world and that top-down, or feedback connections carry predictions for low-level stimuli derived from these hypotheses is Grossberg's ART.