Enhanced Image Classification With a Fast-Learning Shallow Convolutional Neural Network
This method addresses the need for frequent or online retraining in applications by reducing training time and complexity, though it is incremental as it builds on existing neural network approaches.
The paper tackles the problem of slow training in image classification by introducing a fast-learning shallow convolutional neural network, achieving state-of-the-art results with 0.37% error on MNIST and 2.2% error on NORB-small, and competitive 4% error on SVHN, while enabling very rapid training.
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.