Free Deep Learning with Tensorflow and PyTorch Course

Deep Learning with Tensorflow and Pytorch

• Lesson 01: Course Introduction

  05:03

  • 1.01 Course Introduction Foundations and Applications of Deep Learning with TensorFlow and PyTorch

    02:20

  • 1.02 Kickstarting Foundations and Applications of Deep Learning with TensorFlow and PyTorch

    02:43

• Lesson 02: Learning Objectives

  01:09

  • 2.01 Learning Objectives

    01:09

• Lesson 03: Introduction to Deep Learning

  34:07

  • 3.01 Brief History of AI​

    05:45

  • 3.02 Motivation for Deep Learning​

    02:20

  • 3.03 Deep Learning​

    01:15

  • 3.04 Deep Learning vs Machine Learning​

    02:29

  • 3.05 Breakthroughs in Deep Learning Foundations and Early Milestones 2012 2017

    06:03

  • 3.06 Deep Learning Successes in the Last Decade

    01:57

  • 3.07 Key Reasons to Learn Deep Learning

    03:04

  • 3.08 Applications of Deep Learning

    01:32

  • 3.09 Limitations of Deep Learning

    02:06

  • 3.10 Deep Learning Frameworks

    02:35

  • 3.11 Lifecycle of a Deep Learning Project

    05:01

• Lesson 04: Artificial Neural Networks

  01:24:27

  • 4.01 Neurons

    03:14

  • 4.02 Neural Networks

    01:14

  • 4.03 Types of Neural Networks

    03:43

  • 4.04 Neural Network Architecture

    03:03

  • 4.05 Perceptron

    06:32

  • 4.06 Demo Perceptron Based Classification Model

    09:16

  • 4.07 Activation Function

    06:07

  • 4.08 ReLU vs Sigmoid Function

    01:27

  • 4.09 Demo Configuring Neural Network and Activation Function

    08:39

  • 4.10 Forward Propagation in Perceptron

    01:20

  • 4.11 What Is Loss Function​

    01:42

  • 4.12 What Is Cost Function

    02:32

  • 4.13 Backpropagation in Perceptron​

    04:43

  • 4.14 A Feed Forward Network​

    02:10

  • 4.15 Forward Pass​

    02:51

  • 4.16 Calculating Total Error​

    01:24

  • 4.17 Backward Pass​

    05:36

  • 4.18 Updated Weight ​

    01:33

  • 4.19 Hidden Layer Weight Assignment​

    03:47

  • 4.20 Vanishing Gradient​

    01:15

  • 4.21 Exploding Gradient​

    00:46

  • 4.22 Gradient Desent

    04:07

  • 4.23 Gradient Ascent​

    04:23

  • 4.24 The Learning Rate​

    01:09

  • 4.25 Limitation of a Perceptron

    01:54

• Lesson 05: Deep Neural Networks

  01:04:39

  • 5.01 Introduction to Deep Neural Network DNN​

    03:44

  • 5.02 Loss Function in DNN​

    02:11

  • 5.03 Loss Function and Its Major Categories Regression Loss

    00:53

  • 5.04 Types of Regression Loss Mean Absolute Error

    02:10

  • 5.05 Types of Regression Loss Mean Squared Error

    01:50

  • 5.06 MSE vs MAE

    01:47

  • 5.07 Backpropagation with MSE Binary and Multiclass Classification

    01:22

  • 5.08 Types of Classification Loss

    04:36

  • 5.09 Types of Cross Entropy Loss

    06:03

  • 5.10 Types of Classification Loss Hinge loss

    06:08

  • 5.11 Properties of Hinge Loss

    01:09

  • 5.12 Squared Hinge Loss

    01:13

  • 5.13 Forward Propagation in DNN​

    02:17

  • 5.14 Demo Working on Forward Propagation

    06:44

  • 5.15 Backward Propagation in DNN​

    02:50

  • 5.16 The Overfitting Problem

    02:13

  • 5.17 Regularization

    04:54

  • 5.18 Lesson End Project MNIST Image Classification

    12:35

• Lesson 06: TensorFlow

  02:55:35

  • 6.01 Introduction to TensorFlow​

    04:21

  • 6.02 Why Is TensorFlow Necessary

    02:56

  • 6.03 Categories of TensorFlow APIs​

    04:26

  • 6.04 Applications of TensorFlow​

    04:22

  • 6.05 Demo Introduction to Tensors Part 1

    08:49

  • 6.06 Demo Introduction to Tensors Part 2

    12:41

  • 6.07 Demo Hands on with TensorFlow Part 1

    11:17

  • 6.08 Demo Hands on with TensorFlow Part 2

    13:00

  • 6.09 Demo Training DNN Using TensorFlow

    11:47

  • 6.10 Installation of TensorFlow

    03:31

  • 6.11 TensorFlow Playground

    01:29

  • 6.12 Hands on with TensorFlow Playground

    04:41

  • 6.13 TFLearn​

    05:58

  • 6.14 Built In Operations of TFLearn

    05:09

  • 6.15 Visualization

    02:51

  • 6.16 Introduction to Keras

    01:34

  • 6.17 Keras Supported Frameworks and Key Features

    01:10

  • 6.18 Keras Backends

    01:28

  • 6.19 Advantages of Keras

    02:41

  • 6.20 Keras API Components Layers and Models

    01:50

  • 6.21 Sequential and Functional API in Keras

    03:30

  • 6.22 Demo Sequential APIs in TensorFlow Part 1

    13:35

  • 6.23 Demo Sequential APIs in TensorFlow Part 2

    13:41

  • 6.24 Demo Functional APIs in TensorFlow Part 1

    09:18

  • 6.25 Demo Functional APIs in TensorFlow Part 2

    10:55

  • 6.26 Creating a Keras Model

    06:01

  • 6.27 Implementation of Loss Function

    00:37

  • 6.28 Demo Hands on with TensorFlow and Keras

    11:57

• Lesson 07: PyTorch

  32:11

  • 7.01 Introduction to PyTorch ​

    02:01

  • 7.02 PyTorch vs Keras​

    02:02

  • 7.03 Industrial Use Cases of PyTorch and Keras​

    01:15

  • 7.04 PyTorch Key Characteristics and Emerging Trends

    01:51

  • 7.05 PyTorch Ecosystems​

    01:27

  • 7.06 Installation of PyTorch

    01:19

  • 7.07 PyTorch Tensors​

    01:44

  • 7.08 Modules in PyTorch​

    03:58

  • 7.09 Building a DL Model with the Fashion MNIST Dataset​

    00:58

  • 7.10 First Three Steps of Building a Deep Learning Model

    04:48

  • 7.11 Last Two Steps of Building a Deep Learning

    05:10

  • 7.12 Example MNIST Digit Classifier​

    05:38

• Lesson 08: Model Optimization and Performance Improvement

  03:06:57

  • 8.01 Optimization Essentials Concepts Examples and Algorithms

    03:13

  • 8.02 Importance of Optimization Algorithms

    01:57

  • 8.03 Overview of Optimizers Meaning Types and Examples

    03:14

  • 8.04 Introduction to Gradient Descent​

    06:16

  • 8.05 Stochastic Gradient Descent

    03:06

  • 8.06 Mini Batch SGD and How It Differs from Gradient Descent

    02:17

  • 8.07 Demo Implementation of SGD Part 1

    12:15

  • 8.08 Demo Implementation of SGD Part 2

    07:00

  • 8.09 Introduction to Momentum

    03:37

  • 8.10 SGD and NAG with Momentum

    03:57

  • 8.11 Demo Implementation of Momentum Part 1

    09:49

  • 8.12 Demo Implementation of Momentum Part 2

    08:13

  • 8.13 Introduction to AdaGrad​

    05:05

  • 8.14 Demo Implementation of AdaGrad

    13:06

  • 8.15 Introduction to RMSProp

    04:25

  • 8.16 Demo Implementation of RMSProp

    06:06

  • 8.17 Adadelta Selecting the Right Algorithm​

    01:40

  • 8.18 Adadelta Equation​

    02:52

  • 8.19 Adaptive Optimizers Adadelta and Adam Overview

    02:00

  • 8.20 Demo Implementation of Adadelta

    06:12

  • 8.21 Adam Optimizer​

    05:00

  • 8.22 Demo Implementation of Adam

    06:32

  • 8.23 Data Preprocessing and Normalization

    02:09

  • 8.24 Batch Normalization Process​

    02:17

  • 8.25 Implementing and Applying Batch Normalization Using Keras

    01:33

  • 8.26 Reguralization

    00:36

  • 8.27 Regularization in Machine Learning Purpose and Types

    01:24

  • 8.28 Improving Model Training Loss Sampling and Training Strategies

    04:14

  • 8.29 Dropout in Neural Networks Concepts and Usage

    02:15

  • 8.30 Dropout in Neural Networks Usage and Best Practices

    05:27

  • 8.31 Demo Implementation of Dropout

    09:11

  • 8.32 Vanishing Gradient

    02:56

  • 8.33 Exploding Gradient

    01:32

  • 8.34 Hyperparameter Tuning​

    06:04

  • 8.35 Manual Hyperparameter Selection and Tuning

    01:51

  • 8.36 Data Partitioning for Hyperparameter Selection

    01:51

  • 8.37 Hyperparameter Tuning Techniques Grid Search

    02:21

  • 8.38 Hyperparameter Tuning Techniques Random Search

    02:16

  • 8.39 Advanced Hyperparameter Optimization Techniques

    01:32

  • 8.40 Interpretability What It Is and Why It Matters

    01:06

  • 8.41 Model Interpretability Concepts Methods and Evaluation

    05:30

  • 8.42 Explainability Meaning and Effectiveness

    02:10

  • 8.43 Interpretability vs Explainability​

    01:01

  • 8.44 Lesson End Project Implementation Hyperparameter Tuning

    09:49

• Lesson 09: Key Takeaways

  01:31

  • 9.01 Key Takeaways

    01:31

  • Knowledge Check