Enhanced Image Classification With a Fast-Learning Shallow Convolutional Neural Network
arXiv:1503.04596
Abstract
We present a neural network architecture and training method designed to enable very rapid training and low implementation complexity. Due to its training speed and very few tunable parameters, the method has strong potential for applications requiring frequent retraining or online training. The approach is characterized by (a) convolutional filters based on biologically inspired visual processing filters, (b) randomly-valued classifier-stage input weights, (c) use of least squares regression to train the classifier output weights in a single batch, and (d) linear classifier-stage output units. We demonstrate the efficacy of the method by applying it to image classification. Our results match existing state-of-the-art results on the MNIST (0.37% error) and NORB-small (2.2% error) image classification databases, but with very fast training times compared to standard deep network approaches. The network's performance on the Google Street View House Number (SVHN) (4% error) database is also competitive with state-of-the art methods.
arXiv comment7 pages, 2 figures, Paper at IJCNN 2015 (International Joint Conference on Neural Networks, 2015)
References in corpus (4)
- Deep Learning in Neural Networks: An Overview
- Deep Big Simple Neural Nets Excel on Handwritten Digit Recognition
- Fast, simple and accurate handwritten digit classification by training shallow neural network classifiers with the 'extreme learning machine' algorithm
- Constrained Extreme Learning Machines: A Study on Classification Cases