Example receptive fields of neurons in competitive columns of the 4G1P model. (A) The learned feedback (FB) weights of a single border ownership column. Eight neurons are depicted, with two for each orientation. The neurons learn to compete over polarities for each orientation. Green indicates an excitatory connection and red an inhibitory connection. Feedback is learned from both the grouping and the proto-object layer. (B–E) The learned feedforward (FF) weights of four proto-object neurons. The proto-object layer has columns with single neurons. Feedforward input is colored based on the preferred polarity of the border ownership neuron that supplied the input. Input comes from both border ownership and grouping neurons: any input from a grouping neuron is colored by tracing its feedforward inputs to the border ownership layer. (F–I) Learned feedforward and feedback connections for four grouping neuron columns. Column size is dependent on the random distribution of neurons in the grouping layer, so some columns have fewer than four neurons. The top row in each inset depicts learned feedforward weights, colored as in the proto-object columns. The bottom row depicts the learned feedback weights from the proto-object layer, colored as in the border ownership column. The figure is best viewed digitally, zoomed in.
This site uses cookies. By continuing to use our website, you are agreeing to our privacy policy. No content on this site may be used to train artificial intelligence systems without permission in writing from the MIT Press.