资源分类
》 资源 》论文》A Boo(n) for Evaluating Architecture Performance

A Boo(n) for Evaluating Architecture Performance

2020-03-16 | |  62 |   35 |   0

Abstract

We point out important problems with the common practice of using the best single model performance for comparing deep learning architectures, and we propose a method that corrects these flaws. Each time a model is trained, one gets a different result due to random factors in the training process, which include random parameter initialization and random data shuffling. Reporting the best single model performance does not appropriately address this stochasticity. We propose a normalized expected best-out-of-n performance (Boon ) as a way to correct these problems.

上一篇：Orthogonal Recurrent Neural Networks with Scaled Cayley Transform

下一篇：Transfer in Deep Reinforcement Learning Using Successor Features and Generalised Policy Improvement

用户评价
全部评价

热门资源

  • The Variational S...

    Unlike traditional images which do not offer in...

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Rating-Boosted La...

    The performance of a recommendation system reli...