Nonlinear Computing and Nonlinear Artificial Intelligence
The importance and the necessity of nonlinearity in Artificial Intelligence, AI, and deep learning are very well understood. A multi-layer neural network with linear activation function is equivalent to a single layer of neurons. It is nonlinearity of activation functions that adds complexity to each layer, transforming the network to a universal computing machine that can approximate any continuous function. However, nonlinearity and the complexity that it creates have not been investigated enough in AI and modern deep learning systems. NC State University’s Nonlinear Artificial Intelligence Lab focuses on nonlinearity and the complexity that comes with it, and investigates how this can be an engine of artificial intelligence. We peruse our research at different levels with different goals. In this article we explain our approach, and present an overview of our results.
- 2.M.D. Fox, A.Z. Snyder, J.L. Vincent, M. Corbetta, D.C. Van Essen, M.E. Raichle, The human brain is intrinsically organized into dynamic, anticorrelated functional networks. Proc. Natl. Acad. Sci. U.S.A. 102, 9673-9678 (2005)Google Scholar
- 6.A. Blum, R.L. Rivest, Training a 3-node neural network is NP-complete. Advances in neural information processing systems (1989)Google Scholar
- 8.A. Krizhevsky, I. Sutskever, G.E. Hinton, Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems (2012)Google Scholar
- 11.B. Kia, K. Mobley, W.L. Ditto, An integrated circuit design for a dynamics-based reconfigurable logic block. IEEE Trans. Circuits Syst. II: Express Briefs (2017)Google Scholar
- 12.B. Kia et al., Nonlinear dynamics-based adaptive hardware, in 2017 NASA/ESA Conference on Adaptive Hardware and Systems (AHS) (IEEE, 2017)Google Scholar