Training Binary Multilayer Neural Networks for Image Classification using Expectation Backpropagation
This work addresses efficiency improvements for hardware implementation in image classification, but it is incremental as it extends known methods to new tasks.
The paper tackled the problem of training binary multilayer neural networks (BMNNs) for multiclass image classification using the Expectation BackPropagation (EBP) algorithm, achieving test errors of 2.12% with binary weights and 1.66% with real weights on MNIST, comparable to standard BackPropagation.
Compared to Multilayer Neural Networks with real weights, Binary Multilayer Neural Networks (BMNNs) can be implemented more efficiently on dedicated hardware. BMNNs have been demonstrated to be effective on binary classification tasks with Expectation BackPropagation (EBP) algorithm on high dimensional text datasets. In this paper, we investigate the capability of BMNNs using the EBP algorithm on multiclass image classification tasks. The performances of binary neural networks with multiple hidden layers and different numbers of hidden units are examined on MNIST. We also explore the effectiveness of image spatial filters and the dropout technique in BMNNs. Experimental results on MNIST dataset show that EBP can obtain 2.12% test error with binary weights and 1.66% test error with real weights, which is comparable to the results of standard BackPropagation algorithm on fully connected MNNs.