(Old) Lecture 6 | Acceleration, Regularization, and Normalization
Carnegie Mellon University
Course: 11-785, Intro to Deep Learning
Offering: Spring 2019
Slides: http://deeplearning.cs.cmu.edu/slides.spring19/lecture_6_SGD.pdf
For more information, please visit: http://deeplearning.cs.cmu.edu/
Content:
• Stochastic gradient descent
• Optimization
• Acceleration
• Overfitting and regularization
• Tricks of the trade:
– Choosing a divergence (loss) function
– Batch normalization
– Dropout
