Visualizations of Deep Learning, Recurrent Neural Networks, and Evolutionary Algorithms
Thursday, November 19, 2009
I evolved a recurrent neural network (Elman network with 5 hidden sine nodes) on the 89-state maze task (described here) using CMA-ES (thanks to Nikolaus Hansen for making his source code publicly available!), and was able to get good results (approx. 52 time-steps to solve, averaged over 1000 trials.) Each time an improved solution was found, the parameters were written to a text file. The above graphic visualizes the progression of the parameters through time.