Hybrid Learning Network: A Novel Architecture for Fast Learning
Ying Liu, Chao Jian Xiang · Procedia Computer Science · 2017
There’re many effective architectures of the artificial neural network(ANN). For which the training is a hard work. The cost for training an ANN increases exponentially when the ANN gets deeper or wider. We therefore propose a novel architecture, the Hybrid Learning Network(HLN), to achieve a fast learning with good stablity. The HLN can learn from both labeled data and unlabeled data at the same time in a hybrid learning manner. It uses a Self Organizing Map unified by the specially designed nonlinear function as the sparsity mask for a hidden layer to improve the training speed. We experiment our architecture on a synthetic dataset to test its regression capability against the traditional architecture, the result is promising.