资源分类
》 资源 》论文》Compete to Compute

Compete to Compute

2020-01-16 | |  189 |   125 |   0

Abstract

Local competition among neighboring neurons is common in biological neural networks (NNs). In this paper, we apply the concept to gradient-based, backprop-trained artificial multilayer NNs. NNs with competing linear units tend to outperform those with non-competing nonlinear units, and avoid catastrophic forgetting when training sets change over time.

上一篇：Robust Spatial Filtering with Beta Divergence

下一篇：Global Solver and Its Efficient Approximation for Variational Bayesian Low-rank Subspace Clustering

用户评价
全部评价

热门资源

  • Deep Cross-media ...

    Cross-media retrieval is a research hotspot in ...

  • Regularizing RNNs...

    Recently, caption generation with an encoder-de...

  • Learning Expressi...

    Facial expression is temporally dynamic event w...

  • Attributed Graph ...

    Graph clustering is a fundamental task which di...

  • Compact MDDs for ...

    Pseudo-Boolean (PB) constraints are usually en...