Shallow Network Performance in an Increasing Image Dimension
This paper describes the performance of a shallow network towards increasing complexity of dimension in an image input representation. This paper will highlight the generalization problem in Shallow Neural Network despite its extensive usage. In this experiment, a backpropagation algorithm is chosen to test the network as it is widely used in many classification problems. A set of three different size of binary images are used in this experiment. The idea is to assess how the network performs as the scale of the input dimension increases. In addition, a benchmark MNIST handwritten digit sampling is also used to test the performance of the shallow network. The result of the experiment shows the network performance as the scale of input increases. The result is then discussed and explained. From the conducted experiments it is believed that the complexity of the input size and breadth of the network affects the performance of the Neural Network. Such results can be as a reference and guidance to people that is interested in doing research using backpropagation algorithm.
KeywordsNeural Network Shallow network Backpropagation Image recognition
- 2.Tara, N.S., Brian, K., George, S., Hagen, S., Abdel-rahman, M., George, D., Bhuvana, R.: Deep convolutional neural networks for large-scale speech tasks. Neural Netw. 64, 39–48 (2014)Google Scholar
- 16.LeCun, Y., Boser, B., Denker, J.S., Henderson, D., Howard, R.E., Hubbard, W., Jackel, L.D.: Handwritten digit recognition with a back-propagation network. In: Touretzky, D.S. (ed.) Advances in Neural Information Processing Systems, vol. 2, pp. 396–404 (1990)Google Scholar
- 19.Warren, S., Mcculloch, W.P.: A logical calculus of the ideas immanent in nervous activity 5, 115–133 (1943)Google Scholar
- 20.Jeff, H.: Introduction to Neural Networks for Java, 2nd edn., pp. 1–440 (2008)Google Scholar
- 21.Abdul-Rahman, S., Bakar, A.A., Mohamed-Hussein, Z.-A.: An intelligent data pre-processing of complex datasets. Intell. Data Anal. 16, 305–325 (2012)Google Scholar