Evolution of Active Categorical Image Classification via Saccadic Eye Movement
Pattern recognition and classification is a central concern for modern information processing systems. In particular, one key challenge to image and video classification has been that the computational cost of image processing scales linearly with the number of pixels in the image or video. Here we present an intelligent machine (the “active categorical classifier,” or ACC) that is inspired by the saccadic movements of the eye, and is capable of classifying images by selectively scanning only a portion of the image. We harness evolutionary computation to optimize the ACC on the MNIST hand-written digit classification task, and provide a proof-of-concept that the ACC works on noisy multi-class data. We further analyze the ACC and demonstrate its ability to classify images after viewing only a fraction of the pixels, and provide insight on future research paths to further improve upon the ACC presented here.
KeywordsActive categorical perception Attention-based processing Evolutionary computation Machine learning Supervised classification
We thank David B. Knoester, Arend Hintze, and Jeff Clune for their valuable input during the development of this project. We also thank the Michigan State University High Performance Computing Center for the use of their computing resources. This work was supported in part by the National Science Foundation BEACON Center under Cooperative Agreement DBI-0939454, and in part by National Institutes of Health grants LM009012, LM010098, and EY022300.
- 3.Mnih, V., Heess, N., Graves, A., Kavukcuoglu, K.: Recurrent models of visual attention. In: Advances in Neural Information Processing Systems, NIPS 2009, pp. 2204–2212 (2014)Google Scholar
- 11.Olson, R.S., Knoester, D.B., Adami, C.: Evolution of swarming behavior is shaped by how predators attack. Artif. Life 22 (2016)Google Scholar
- 12.Breiman, L., Cutler, A.: Random forests - classification description, March 2016. http://www.stat.berkeley.edu/~breiman/RandomForests/cc_home.htm
- 14.Wan, L., Zeiler, M., Zhang, S., LeCun, Y., Fergus, R.: Regularization of neural networks using DropConnect. In: Proceedings of the 30th International Conference on Machine Learning, ICML 2013 (2013)Google Scholar
- 16.Nguyen, A., Yosinski, J., Clune, J.: Neural networks are easily fooled: high confidence predictions for unrecognizable images. In: Computer Vision and Pattern Recognition (CVPR 2015). IEEE Press (2015)Google Scholar
- 17.Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. In: International Conference on Learning Representations (2015). http://research.google.com/pubs/ChristianSzegedy.html
- 18.Szegedy, C., Zaremba, W., Sutskever, I., et al.: Intriguing properties of neural networks. In: International Conference on Learning Representations (2014). http://research.google.com/pubs/ChristianSzegedy.html