Abstract:
We present the soft exponential activation function for artificial neural networks that continuously interpolates between logarithmic, linear, and exponential functions. ...Show MoreMetadata
Abstract:
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, and sinusoids.
Published in: 2015 7th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management (IC3K)
Date of Conference: 12-14 November 2015
Date Added to IEEE Xplore: 01 August 2016
ISBN Information:
Conference Location: Lisbon, Portugal