10.1371/journal.pone.0085175.g002 Michael Alexander Nugent Michael Alexander Nugent Timothy Wesley Molter Timothy Wesley Molter Attractor states of a two-input AHaH node. Public Library of Science 2014 Computational biology computational neuroscience Circuit models Coding mechanisms neuroscience Cognitive neuroscience cognition Decision making Motor reactions Sensory systems Visual system Learning and memory Motor systems neural networks algorithms Computer architecture Computer hardware Computing systems Hybrid computing text mining Electrical engineering Electronics engineering Solid state physics states two-input ahah 2014-02-10 03:23:44 Figure https://plos.figshare.com/articles/figure/_Attractor_states_of_a_two_input_AHaH_node_/929347 <p>The AHaH rule naturally forms decision boundaries that maximize the margin between data distributions (black blobs). This is easily visualized in two dimensions, but it is equally valid for any number of inputs. Attractor states are represented by decision boundaries A, B, C (green dotted lines) and D (red dashed line). Each state has a corresponding anti-state: . State A is the null state and its occupation is inhibited by the bias. State D has not yet been reliably achieved in circuit simulations.</p>