L.V.'s Blog – October 2018 Archive (1)
Deep Learning Networks: Advantages of ReLU over Sigmoid Function
This was posted as a question on StackExchange. The state of the art of non-linearity is to use rectified linear units (ReLU) instead of sigmoid function in deep neural network. What are the advantages? I know that training a network when ReLU is used would be faster, and it is more biological inspired, what are the other advantages? (That is, any disadvantages of using sigmoid)?…
ContinueAdded by L.V. on October 11, 2018 at 6:00pm — No Comments
Latest Blog Posts
- Deep Learning Networks: Advantages of ReLU over Sigmoid Function
- Deep Learning: AlphaGo Zero Explained In One Picture
- Choosing the Correct Type of Regression Analysis
- Book: Machine Learning: a Probabilistic Perspective
- Handbook of Statistical Analysis and Data Mining Applications - 2nd Edition
- The Gaussian Correlation Inequality in One Picture
- Machine Learning Glossary by Google
Most Popular Blog Posts
- 32 New External Machine Learning Resources and Updated Articles
- Data scientist paid $500k can barely code!
- 6 Types of Programmers in One Picture
- Deep Learning Cheat Sheet (using Python Libraries)
- 600 websites about R
- 27 Best "Picture of the Week" Over the Last 12 Months
- 18 Reasons Data Scientists are Difficult to Manage
Resources
Videos
© 2020 Data Science Central ®
Powered by
Badges | Report an Issue | Privacy Policy | Terms of Service
