A continuum among logarithmic, linear, and exponential functions, and its potential to improve generalization in neural networks
We present the soft exponential activation function for artificial neural networks that continuously interpolates between logarithmic, linear, and exponential functions. This activation function is simple, differentiable, and parameterized so that it can be trained as the rest of the network is trained. We hypothesize that soft exponential has the potential to improve neural network learning, as it can exactly calculate many natural operations that typical neural networks can only approximate, including addition, multiplication, inner product, distance, polynomials, and sinusoids.
- Pub Date:
- February 2016
- Computer Science - Neural and Evolutionary Computing
- 6 pages, 8 figures, conference, In Proceedings of Knowledge Discovery and Information Retrieval (KDIR) 2015, Lisbon, Portugal, December 2015