Deep Learning and Computer Vision Stanford Li Feifei

Computer vision has become ubiquitous in our society with applications in search, image recognition, apps, imaging, medicine, drones, and self-driving cars. Many of these applications, such as: image classification, localization and detection, are completed by visual recognition technology. Newly discovered neural network methods (also known as "deep learning") have greatly improved the advanced performance of visual recognition systems.

• Chapter 1：Course Introduction - Computer Vision Overview (7 minutes and 29 seconds)

• Chapter 2：Course Introduction- Historical Background of Computer Vision (29 minutes and 30 seconds)

• Chapter 3：Course Introduction - Course Logistics (22 minutes and 22 seconds)

• Chapter 4：Image Classification - Data-Driven Approach (23 minutes and 50 seconds)

• Chapter 5：Image Classification - K Nearest Neighbor Algorithm (23 minutes and 8 seconds)

• Chapter 6：Image Classification - Linear Classification I (13 minutes and 55 seconds)

• Chapter 7：Loss Functions and Optimization - Loss Functions (50 minutes and 8 seconds)

• Chapter 8：Loss Functions and Optimization - Optimization (25 minutes and 30 seconds)

• Chapter 9：Introduction to Neural Networks - Backpropagation (55 minutes and 40 seconds)

• Chapter 10：Introduction to Neural Networks – Neural Networks (19 minutes and 12 seconds)

• Chapter 11：Convolutional Neural Networks - History (14 minutes and 15 seconds)

• Chapter 12：Convolutional Neural Networks - Convolution and Pooling (36 minutes and 55 seconds)

• Chapter 13：Convolutional Neural Networks - Convolutional Neural Networks Beyond Vision (19 minutes and 3 seconds)

• Chapter 14：activation function (49 minutes and 21 seconds)

• Chapter 15：batch normalization (31 minutes and 54 seconds)

• Chapter 16：better optimization (55 minutes and 18 seconds)

• Chapter 17：Regularization (15 minutes and 15 seconds)

• Chapter 18：transfer learning (6 minutes and 21 seconds)

• Chapter 19：Caffe, Torch, Theano, TensorFlow, Keras, PyTorch and more (1 hours and 18 minutes and 35 seconds)

• Chapter 20：AlexNet, VGG, GoogLeNet, ResNet, etc. (1 hours and 18 minutes and 7 seconds)

• Chapter 21：RNN, LSTM, GRU (21 minutes and 13 seconds)

• Chapter 22：language model (22 minutes and 7 seconds)

• Chapter 23：Image annotation, visual question answering, soft attention model (34 minutes and 31 seconds)

• Chapter 24：segmentation (33 minutes and 23 seconds)

• Chapter 25：position (10 minutes and 17 seconds)

• Chapter 26：identify (32 minutes and 40 seconds)

• Chapter 27：Feature visualization, inversion, adversarial examples (52 minutes and 15 seconds)

• Chapter 28：DeepDream and style transfer (24 minutes and 33 seconds)

• Chapter 29：Pixel RNN CNN (20 minutes and 6 seconds)

• Chapter 30：variational autoencoder (33 minutes and 50 seconds)

• Chapter 31：Generative Adversarial Network (30 minutes and 34 seconds)

• Chapter 32：Policy gradient, hard attention (21 minutes and 13 seconds)

• Chapter 33：Q-Learning, Actor-Critic Algorithm (49 minutes and 2 seconds)

• Chapter 34：Deep learning methods and hardware (1 hours and 17 minutes and 38 seconds)

• Chapter 35：Adversarial examples and adversarial training (1 hours and 22 minutes and 17 seconds)

• Chapter 36：Special: Conversation with Ian Goodfellow (3 minutes and 59 seconds)

• Chapter 37：Special article: Specially invited dialogue with Song Han (3 minutes and 10 seconds)