Overview

Embark on a comprehensive 22-hour journey through the world of deep learning. Explore the historical context, fundamental concepts, and advanced techniques in this extensive lecture series. Begin with an introduction to machine learning basics and progress through computation graphs, deep neural networks, regularization methods, and optimization strategies. Dive into specialized topics such as convolutional neural networks, sequence models, natural language processing, and graph neural networks. Investigate autoencoders, including variational autoencoders, and conclude with an in-depth look at generative adversarial networks. Gain practical insights into debugging strategies, visualization techniques, and cutting-edge research in the field.

Syllabus

Deep Learning - Lecture 1.1 (Introduction: Organization).
Deep Learning - Lecture 1.2 (Introduction: History of Deep Learning).
Deep Learning - Lecture 1.3 (Introduction: Machine Learning Basics).
Deep Learning - Lecture 2.1 (Computation Graphs: Logistic Regression).
Deep Learning - Lecture 2.2 (Computation Graphs: Computation Graphs).
Deep Learning - Lecture 2.3 (Computation Graphs: Backpropagation).
Deep Learning - Lecture 2.4 (Computation Graphs: Educational Framework).
Deep Learning - Lecture 3.1 (Deep Neural Networks: Backpropagation with Tensors).
Deep Learning - Lecture 3.2 (Deep Neural Networks: The XOR Problem).
Deep Learning - Lecture 3.3 (Deep Neural Networks: Multi-Layer Perceptrons).
Deep Learning - Lecture 3.4 (Deep Neural Networks: Universal Approximation).
Deep Learning - Lecture 4.1 (Deep Neural Networks II: Output and Loss Functions).
Deep Learning - Lecture 4.2 (Deep Neural Networks II: Activation Functions).
Deep Learning - Lecture 4.3 (Deep Neural Networks II: Preprocessing and Initialization).
Deep Learning - Lecture 5.1 (Regularization: Parameter Penalties).
Deep Learning - Lecture 5.2 (Regularization: Early Stopping).
Deep Learning - Lecture 5.3 (Regularization: Ensemble Methods).
Deep Learning - Lecture 5.4 (Regularization: Dropout).
Deep Learning - Lecture 5.5 (Regularization: Data Augmentation).
Deep Learning - Lecture 6.1 (Optimization: Optimization Challenges).
Deep Learning - Lecture 6.2 (Optimization: Optimization Algorithms).
Deep Learning - Lecture 6.3 (Optimization: Optimization Strategies).
Deep Learning - Lecture 6.4 (Optimization: Debugging Strategies).
Deep Learning - Lecture 7.1 (Convolutional Neural Networks: Convolution).
Deep Learning - Lecture 7.2 (Convolutional Neural Networks: Downsampling).
Deep Learning - Lecture 7.3 (Convolutional Neural Networks: Upsampling).
Deep Learning - Lecture 7.4 (Convolutional Neural Networks: Architectures).
Deep Learning - Lecture 7.5 (Convolutional Neural Networks: Visualization).
Deep Learning - Lecture 8.1 (Sequence Models: Recurrent Networks).
Deep Learning - Lecture 8.2 (Sequence Models: Recurrent Network Applications).
Deep Learning - Lecture 8.3 (Sequence Models: Gated Recurrent Networks).
Deep Learning - Lecture 8.4 (Sequence Models: Autoregressive Models).
Deep Learning - Lecture 9.1 (Natural Language Processing: Language Models).
Deep Learning - Lecture 9.2 (Natural Language Processing: Traditional Language Models).
Deep Learning - Lecture 9.3 (Natural Language Processing: Neural Language Models).
Deep Learning - Lecture 9.4 (Natural Language Processing: Neural Machine Translation).
Deep Learning - 10.1 (Graph Neural Networks: Machine Learning on Graphs).
Deep Learning - 10.2 (Graph Neural Networks: Graph Convolution Filters).
Deep Learning - 10.3 (Graph Neural Networks: Graph Convolution Networks).
Deep Learning - Lecture 11.1 (Autoencoders: Latent Variable Models).
Deep Learning - Lecture 11.2 (Autoencoders: Principal Component Analysis.
Deep Learning - Lecture 11.3 (Autoencoders: Autoencoders).
Deep Learning - Lecture 11.4 (Autoencoders: Variational Autoencoders).
Deep Learning - Lecture 12.1 (Generative Adversarial Networks: Generative Adversarial Networks).
Deep Learning - Lecture 12.2 (Generative Adversarial Networks: GAN Developments).
Deep Learning - Lecture 12.3 (Generative Adversarial Networks: Research at AVG).