Latent learning in deep neural nets

Psychologists define latent learning as learning that occurs without task-specific reinforcement and is not demonstrated until needed. Since this knowledge is acquired while mastering some other task(s), it is a form of transfer learning. We utilize latent learning to enable a deep neural net to distinguish among a set of handwritten numerals. The accuracies obtained are compared to those achievable with a simplistic `group-mean´ classification technique, which is explained later in this paper. The deep neural net architecture used was a Le-Net 5 convolutional neural net with only minor differences in the output layer.