Enhanced image classification with a fast-learning shallow convolutional neural network

By Mark D. McDonnell, Tony Vladusich. 2015

85 citations recorded by the source corpus.

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 the absence of iteratively-tuned 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.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Understanding Data Augmentation for Classification: When to Warp? (2016, methodology): “To enable comparison of data augmentation for a convolutional neural network (CNN), a convolutional support vector machine (CSVM) [8], and a convolutional extreme learning machine (CELM) [9] classiﬁer, we use the well known MNIST handwritten digit dataset [10].”
An Exploration of Parameter Redundancy in Deep Networks with Circulant Projections (2015, methodology): “Our method is also related to the recent efforts of “shallow” neural networks, which show that sometimes shallow structures can match the performance of deep structures [28, 27, 19, 44].”