291 Programming Assignment # 3

We train two convolutional neural networks on the POFA and NimStim datasets to identify individuals and identify emotions, respectively. In order to train these neural networks, we use two separate optimization procedures, the minFunc package and stochastic gradient descent. The minFunc optimization package achieved a 95.8% on the training set and achieved a 90.0% accuracy on the partitioned test set. Stochastic gradient descent achieved a 99.4% accuracy on the training set and a 89.7% accuracy on the partitioned test set. The minFunc optimization packaged achieved a 91.7% on the training set and achieved a 78.6% accuracy on the partitioned test set. Stochastic gradient descent achieved a 91.7% accuracy on the training set and a 77.2% accuracy on the partitioned test set.