- Reinforcement Learning with TensorFlow
- Sayon Dutta
- 69字
- 2021-08-27 18:51:54
What is xavier initialization?
Xavier Initialization is the initialization of weights in the neural networks, as a random variable following the Gaussian distribution where the variance being given by
Where, is the number of units in the current layer, that is, the incoming signal units, and
is the number of units in the next layer, that is, the outgoing resulting signal units. In short,
is the shape of
.
推薦閱讀
- 大數(shù)據(jù)管理系統(tǒng)
- 軟件架構(gòu)設(shè)計
- Managing Mission:Critical Domains and DNS
- 大數(shù)據(jù)專業(yè)英語
- TIBCO Spotfire:A Comprehensive Primer(Second Edition)
- 數(shù)據(jù)挖掘?qū)嵱冒咐治?/a>
- 計算機系統(tǒng)結(jié)構(gòu)
- Docker on Amazon Web Services
- Linux Shell編程從初學(xué)到精通
- Machine Learning Algorithms(Second Edition)
- 深度學(xué)習(xí)原理與 TensorFlow實踐
- Unreal Development Kit Game Design Cookbook
- PHP求職寶典
- EJB JPA數(shù)據(jù)庫持久層開發(fā)實踐詳解
- 微機組裝與維護教程