Abstract: The sigmoid function is a representative activation function in shallow neural networks. Its hardware realization is challenging due to the complex exponential and reciprocal operations.
Centro de Modelamiento Matemático, Facultad de Ciencias Físicas y Matemáticas, Universidad de Chile, Santiago, Chile. Division of Biostatistics, School of Public Health, University of Minnesota, ...
Abstract: In this letter, we consider the application of max-plus-linear approximators for Q-function in offline reinforcement learning of discounted Markov decision processes. In particular, we ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback