Advances in Artificial Neural Systems / 2009 / Article / Fig 3

Research Article

Building Recurrent Neural Networks to Implement Multiple Attractor Dynamics Using the Gradient Descent Method

Figure 3

Error and Kullback-Leibler divergence between the teaching sequences and output generated by the RNN for 20 000 learning steps in experiment 1.
846040.fig.003a
(a)
846040.fig.003b
(b)

Article of the Year Award: Outstanding research contributions of 2020, as selected by our Chief Editors. Read the winning articles.