Unsupervised Learning of Overlapping Image Components Using Divisive Input Modulation
A simple two-node, two-input, neural network
illustrating the architecture employed by all the algorithms described in this
article. Nodes are shown as large circles, excitatory synapses as arrows and
inhibitory synapses as small filled circles. Reciprocal feedforward and
feedback connections have identical strengths.
Article of the Year Award: Outstanding research contributions of 2020, as selected by our Chief Editors. Read the winning articles.