Section 1 : Welcome
|
Lecture 1 | Introduction | 00:03:53 Duration |
|
Lecture 2 | Outline | 00:12:38 Duration |
|
Lecture 3 | Where to get the code | 00:08:16 Duration |
Section 2 : Google Colab
|
Lecture 1 | Intro to Google Colab, how to use a GPU or TPU for free | 00:12:22 Duration |
|
Lecture 2 | Tensorflow 2 | 00:07:45 Duration |
|
Lecture 3 | Uploading your own data to Google Colab | 00:11:32 Duration |
|
Lecture 4 | Where can I learn about Numpy, Scipy, Matplotlib, Pandas, and Scikit-Learn | 00:08:44 Duration |
|
Lecture 5 | Anyone Can Succeed in this Course | 00:11:46 Duration |
Section 3 : Machine Learning and Neurons
|
Lecture 1 | What is Machine Learning | 00:14:16 Duration |
|
Lecture 2 | Code Preparation (Classification Theory) | 00:15:49 Duration |
|
Lecture 3 | Beginner's Code Preamble | 00:04:29 Duration |
|
Lecture 4 | Classification Notebook | 00:08:30 Duration |
|
Lecture 5 | Code Preparation (Regression Theory) | 00:07:07 Duration |
|
Lecture 6 | Regression Notebook | 00:10:25 Duration |
|
Lecture 7 | The Neuron | 00:09:48 Duration |
|
Lecture 8 | How does a model learn | 00:10:44 Duration |
|
Lecture 9 | Making Predictions | 00:06:35 Duration |
|
Lecture 10 | Saving and Loading a Model | 00:04:18 Duration |
|
Lecture 11 | Suggestion Box | 00:02:54 Duration |
Section 4 : Feedforward Artificial Neural Networks
|
Lecture 1 | Artificial Neural Networks Section Introduction | 00:05:50 Duration |
|
Lecture 2 | Beginners Rejoice The Math in This Course is Optional | 00:11:37 Duration |
|
Lecture 3 | Forward Propagation | 00:09:30 Duration |
|
Lecture 4 | The Geometrical Picture | |
|
Lecture 5 | Activation Functions | 00:17:08 Duration |
|
Lecture 6 | Multiclass Classification | 00:08:32 Duration |
|
Lecture 7 | How to Represent Images | |
|
Lecture 8 | Code Preparation (ANN) | 00:12:32 Duration |
|
Lecture 9 | ANN for Image Classification | 00:08:26 Duration |
|
Lecture 10 | ANN for Regression | 00:10:55 Duration |
Section 5 : Convolutional Neural Networks
|
Lecture 1 | What is Convolution (part 1) | 00:16:28 Duration |
|
Lecture 2 | What is Convolution (part 2) | |
|
Lecture 3 | What is Convolution (part 3) | 00:06:32 Duration |
|
Lecture 4 | Convolution on Color Images | 00:15:49 Duration |
|
Lecture 5 | CNN Architecture | 00:20:48 Duration |
|
Lecture 6 | CNN Code Preparation | 00:15:01 Duration |
|
Lecture 7 | CNN for Fashion MNIST | 00:06:36 Duration |
|
Lecture 8 | CNN for CIFAR-10 | 00:04:18 Duration |
|
Lecture 9 | Data Augmentation | 00:08:41 Duration |
|
Lecture 10 | Batch Normalization | 00:05:04 Duration |
|
Lecture 11 | Improving CIFAR-10 Results | 00:10:11 Duration |
Section 6 : Recurrent Neural Networks, Time Series, and Sequence Data
Section 7 : Natural Language Processing (NLP)
|
Lecture 1 | Embeddings | 00:13:02 Duration |
|
Lecture 2 | Code Preparation (NLP) | 00:13:07 Duration |
|
Lecture 3 | Text Preprocessing | 00:05:20 Duration |
|
Lecture 4 | Text Classification with LSTMs | 00:08:09 Duration |
|
Lecture 5 | CNNs for Text | 00:07:59 Duration |
|
Lecture 6 | Text Classification with CNNs | 00:06:01 Duration |
Section 8 : Recommender Systems
|
Lecture 1 | Recommender Systems with Deep Learning Theory | 00:12:58 Duration |
|
Lecture 2 | Recommender Systems with Deep Learning Code | 00:09:05 Duration |
Section 9 : Transfer Learning for Computer Vision
|
Lecture 1 | Transfer Learning Theory | 00:08:02 Duration |
|
Lecture 2 | Some Pre-trained Models (VGG, ResNet, Inception, MobileNet) | 00:05:31 Duration |
|
Lecture 3 | Large Datasets and Data Generators | 00:06:53 Duration |
|
Lecture 4 | 2 Approaches to Transfer Learning | 00:04:42 Duration |
|
Lecture 5 | Transfer Learning Code (pt 1) | 00:10:40 Duration |
|
Lecture 6 | Transfer Learning Code (pt 2) | 00:08:02 Duration |
Section 10 : GANs (Generative Adversarial Networks)
|
Lecture 1 | GAN Theory | 00:15:40 Duration |
|
Lecture 2 | GAN Code | 00:12:00 Duration |
Section 11 : Deep Reinforcement Learning (Theory)
|
Lecture 1 | Deep Reinforcement Learning Section Introduction | 00:06:25 Duration |
|
Lecture 2 | Elements of a Reinforcement Learning Problem | 00:20:09 Duration |
|
Lecture 3 | States, Actions, Rewards, Policies | 00:09:15 Duration |
|
Lecture 4 | Markov Decision Processes (MDPs) | 00:09:57 Duration |
|
Lecture 5 | The Return | 00:04:46 Duration |
|
Lecture 6 | Value Functions and the Bellman Equation | 00:09:44 Duration |
|
Lecture 7 | What does it mean to “learn” | 00:07:09 Duration |
|
Lecture 8 | Solving the Bellman Equation with Reinforcement Learning (pt 1) | 00:09:38 Duration |
|
Lecture 9 | Solving the Bellman Equation with Reinforcement Learning (pt 2) | 00:11:51 Duration |
|
Lecture 10 | Epsilon-Greedy | 00:05:59 Duration |
|
Lecture 11 | Q-Learning | 00:14:05 Duration |
|
Lecture 12 | Deep Q-Learning DQN (pt 1) | 00:13:55 Duration |
|
Lecture 13 | Deep Q-Learning DQN (pt 2) | |
|
Lecture 14 | How to Learn Reinforcement Learning | 00:05:47 Duration |
Section 12 : Stock Trading Project with Deep Reinforcement Learning
|
Lecture 1 | Reinforcement Learning Stock Trader Introduction | 00:05:04 Duration |
|
Lecture 2 | Data and Environment | 00:12:13 Duration |
|
Lecture 3 | Replay Buffer | 00:05:30 Duration |
|
Lecture 4 | Program Design and Layout | 00:06:47 Duration |
|
Lecture 5 | Code pt 1 | 00:05:36 Duration |
|
Lecture 6 | Code pt 2 | 00:09:30 Duration |
|
Lecture 7 | Code pt 3 | 00:06:18 Duration |
|
Lecture 8 | Code pt 4 | 00:07:15 Duration |
|
Lecture 9 | Reinforcement Learning Stock Trader Discussion | 00:03:27 Duration |
Section 13 : Advanced Tensorflow Usage
|
Lecture 1 | What is a Web Service (Tensorflow Serving pt 1) | 00:05:45 Duration |
|
Lecture 2 | Tensorflow Serving pt 2 | 00:16:45 Duration |
|
Lecture 3 | Tensorflow Lite (TFLite) | 00:08:19 Duration |
|
Lecture 4 | Why is Google the King of Distributed Computing | 00:08:37 Duration |
|
Lecture 5 | Training with Distributed Strategies | 00:06:50 Duration |
|
Lecture 6 | Using the TPU |
Section 14 : Low-Level Tensorflow
|
Lecture 1 | Differences Between Tensorflow 1 | 00:09:52 Duration |
|
Lecture 2 | Constants and Basic Computation | 00:09:30 Duration |
|
Lecture 3 | Variables and Gradient Tape | 00:12:49 Duration |
|
Lecture 4 | Build Your Own Custom Model | 00:10:37 Duration |
Section 15 : In-Depth Loss Functions
|
Lecture 1 | Mean Squared Error | 00:09:01 Duration |
|
Lecture 2 | Binary Cross Entropy | 00:05:46 Duration |
|
Lecture 3 | Categorical Cross Entropy | 00:07:56 Duration |
Section 16 : In-Depth Gradient Descent
|
Lecture 1 | Gradient Descent | 00:07:43 Duration |
|
Lecture 2 | Stochastic Gradient Descent | 00:04:27 Duration |
|
Lecture 3 | Momentum | 00:05:58 Duration |
|
Lecture 4 | Variable and Adaptive Learning Rates | 00:11:35 Duration |
|
Lecture 5 | Adam | 00:11:09 Duration |
Section 17 : Extras
|
Lecture 1 | Links to TF2 |
Section 18 : Setting up your Environment (FAQ by Student Request)
|
Lecture 1 | How to install Numpy, Scipy, Matplotlib, Pandas, IPython, Theano, and TensorFlow | 00:17:24 Duration |
|
Lecture 2 | Windows-Focused Environment Setup 2018 | 00:20:14 Duration |
|
Lecture 3 | Installing NVIDIA GPU-Accelerated Deep Learning Libraries on your Home Computer | 00:22:15 Duration |
Section 19 : Extra Help With Python Coding for Beginners (FAQ by Student Request)
|
Lecture 1 | How to Code Yourself (part 1) | 00:15:49 Duration |
|
Lecture 2 | How to Code Yourself (part 2) | 00:09:23 Duration |
|
Lecture 3 | Proof that using Jupyter Notebook is the same as not using it | 00:12:25 Duration |
|
Lecture 4 | Is Theano Dead | 00:09:57 Duration |
Section 20 : Effective Learning Strategies for Machine Learning (FAQ by Student Request)
|
Lecture 1 | How to Succeed in this Course (Long Version) | 00:10:17 Duration |
|
Lecture 2 | Is this for Beginners or Experts Academic or Practical Fast or slow-paced | 00:21:58 Duration |
|
Lecture 3 | Machine Learning and AI Prerequisite Roadmap (pt 1) | 00:11:14 Duration |
|
Lecture 4 | Machine Learning and AI Prerequisite Roadmap (pt 2) | 00:16:07 Duration |
Section 21 : Appendix FAQ Finale
|
Lecture 1 | What is the Appendix | 00:02:41 Duration |