Lecture 1 | Introduction to Convolutional Neural Networks for Visual Recognition
57:56Lecture 2 | Image Classification
59:31Lecture 3 | Loss Functions and Optimization
1:14:40Lecture 4 | Introduction to Neural Networks
1:13:59Lecture 5 | Convolutional Neural Networks
1:08:56Lecture 6 | Training Neural Networks I
1:20:19Lecture 7 | Training Neural Networks II
1:15:30Lecture 8 | Deep Learning Software
1:18:07Lecture 9: CNN Architectures (CS231n)
1:17:40Lecture 10: Recurrent Neural Networks (CS231n)
1:13:09Lecture 11: Detection and Segmentation (CS231n)
1:14:26Lecture 12: Visualizing and Understanding (CS231n)
1:15:48Lecture 13: Generative Models (CS231n)
1:17:41Lecture 14: Deep Reinforcement Learning (CS231n)
1:04:01Lecture 15: Efficient Methods and Hardware for Deep Learning (CS231n)
1:16:52Lecture 16: Adversarial Examples and Adversarial Training (CS231n)
1:21:46Lecture 6 | Training Neural Networks I
Stanford Vision & Learning Lab Faculty
This lecture details practical considerations for optimizing deep neural networks, examining various activation functions, data preprocessing strategies, weight initialization schemes, and the mechanism of batch normalization for stabilizing learning.
In Lecture 6 we discuss many practical issues for training modern neural networks. We discuss different activation functions, the importance of data preprocessing and weight initialization, and batch normalization; we also cover some strategies for monitoring the learning process and choosing hyperparameters.
Keywords: Activation functions, data preprocessing, weight initialization, batch normalization, hyperparameter search
Lecture 5 | Convolutional Neural Networks
Next · Lecture 7Lecture 7 | Training Neural Networks II