Extraction of Coherent Information from Non-Overlapping Receptive Fields
It has been suggested that long-range lateral connections in the cortex play a contextual role in that they modulate the gain of the response to primary receptive field input. In the first part of this paper I show that a network with a set of such pre-wired connections has a short-term dynamics that enhances and stabilizes coherent information defined across multiple, non-overlapping receptive fields. In the second part, I suggest a simple Hebbian rule that can develop the required pattern of synaptic strengths and describe two simulations where the networks discover information that is defined only by its coherence across receptive fields.
Cite this item
Floreano, D. (1996). Extraction of Coherent Information from Non-Overlapping Receptive Fields. In C. von der Malsburg, W. von Seelen, J. C. Vorbrueggen, & B. Sendhoff (Editors), Artificial Neural Networks. https://doi.org/10.1007/3-540-61510-5_68
Click Copy to copy the citation, or select the text manually.
icann96.pdf
openaccess
160.78 KB
Adobe PDF
b5b0d7c4a594883be39e913778ae4077