A non-parametric softmax for improving neural attention in time-series forecasting
Sign Up to like & getrecommendations! Published in 2020 at "Neurocomputing"
DOI: 10.1016/j.neucom.2019.10.084
Abstract: Abstract Neural attention has become a key component in many deep learning applications, ranging from machine translation to time series forecasting. While many variations of attention have been developed over recent years, all share a… read more here.
Keywords: series forecasting; time series; attention; series ... See more keywords
A pseudo-softmax function for hardware-based high speed image classification
Sign Up to like & getrecommendations! Published in 2021 at "Scientific Reports"
DOI: 10.1038/s41598-021-94691-7
Abstract: In this work a novel architecture, named pseudo-softmax, to compute an approximated form of the softmax function is presented. This architecture can be fruitfully used in the last layer of Neural Networks and Convolutional Neural… read more here.
Keywords: softmax function; neural networks; pseudo softmax; hardware ... See more keywords
Deep Classification with Linearity-Enhanced Logits to Softmax Function
Sign Up to like & getrecommendations! Published in 2023 at "Entropy"
DOI: 10.3390/e25050727
Abstract: Recently, there has been a rapid increase in deep classification tasks, such as image recognition and target detection. As one of the most crucial components in Convolutional Neural Network (CNN) architectures, softmax arguably encourages CNN… read more here.
Keywords: softmax; function; deep classification; linearity enhanced ... See more keywords