Deep Cascade Learning

In this paper, we propose a novel approach for efficient training of deep neural networks in a bottom-up fashion using a layered structure. Our algorithm, which we refer to as Deep Cascade Learning, is motivated by the Cascade Correlation approach of Fahlman [1] who introduced it in the context of perceptrons. We demonstrate our algorithm on networks of convolutional layers, though its applicability is more general. Such training of deep networks in a cascade, directly circumvents the well-known vanishing gradient problem by ensuring that the output is always adjacent to the layer being trained. We present empirical evaluations comparing our deep cascade training with standard End-End training using back propagation of two convolutional neural network architectures on benchmark image classification tasks (CIFAR-10 and CIFAR100). We then investigate the features learned by the approach and find that better, domain-specific, representations are learned in early layers when compared to what is learned in End-End training. This is partially attributable to the vanishing gradient problem which inhibits early layer filters to change significantly from their initial settings. While both networks perform similarly overall, recognition accuracy increases progressively with each added layer, with discriminative features learnt in every stage of the network, whereas in End-End training, no such systematic feature representation was observed. We also show that such cascade training has significant computational and memory advantages over End-End training, and can be used as a pretraining algorithm to obtain a better performance.