Section 1 : Welcome to AI in R course

Lecture 1 Welcome To The Course 3:0
Lecture 2 Install R and RStudio 6:36
Lecture 3 BONUS Learning Path Pdf
Lecture 4 Get the Materials Pdf
Lecture 5 Install MXnet in R and RStudio 3:14
Lecture 6 Install Mxnet in R- Written Instructions Text
Lecture 7 Install H2o 5:38
Lecture 8 What is Keras 3:30
Lecture 9 Install Keras in R Text

Section 2 : Working with Real Data

Lecture 10 Read in Data From CSV and Excel Files 9:56
Lecture 11 Read in Data from Online HTML Tables-Part 1 4:14
Lecture 12 Read in Data from Online HTML Tables-Part 2 6:24
Lecture 13 Working with External Data in H2o 4:21
Lecture 14 Remove NAs 17:12
Lecture 15 More Data Cleaning 8:5
Lecture 16 Introduction to dplyr for Data Summarizing-Part 1 6:12
Lecture 17 Introduction to dplyr for Data Summarizing-Part 2 4:45
Lecture 18 Exploratory Data Analysis(EDA) Basic Visualizations with R 9:2
Lecture 19 What Are the Most Common Data Types We Will Encounter 3:37

Section 3 : Some Theoretical Foundations

Lecture 20 Difference Between Supervised & Unsupervised Learning 5:32

Section 4 : ANN Intuition

Lecture 21 Plan of Attack 2:52
Lecture 22 The Neuron 16:15
Lecture 23 The Activation Function 8:29
Lecture 24 How do Neural Networks work 12:48
Lecture 25 How do Neural Networks learn
Lecture 26 Gradient Descent 10:13
Lecture 27 Stochastic Gradient Descent 8:45
Lecture 28 Backpropagation 5:22

Section 5 : Build Artificial Neural Networks (ANN) in R

Lecture 29 Neural Network for Binary Classifications 6:52
Lecture 30 Evaluate Accuracy 4:19
Lecture 31 Implement a Multi-Layer Perceptron (MLP) For Supervised Classification 4:46
Lecture 32 Neural Network for Multiclass Classifications 7:4
Lecture 33 Neural Network for Image Type Data 4:32
Lecture 34 Multi-class Classification Using Neural Networks with caret 8:27
Lecture 35 Implement an ANN with H2o For Multi-Class Supervised Classification 10:31
Lecture 36 Implement an ANN Based Classification Using MXNet 8:29
Lecture 37 Implement MLP With Keras 11:13
Lecture 38 Keras MLP On Real Data 9:31
Lecture 39 Keras MLP For Regression 3:36
Lecture 40 Neural Network for Regression
Lecture 41 More on Artificial Neural Networks(ANN) - with neuralnet 9:48
Lecture 42 Implement an ANN Based Regression Using MXNet 3:49
Lecture 43 Identify Variable Importance in Neural Networks

Section 6 : Build Deep Neural Networks (DNN) in R

Lecture 44 Implement a Simple DNN With neuralnet for Binary Classifications 8:9
Lecture 45 Implement a Simple DNN With deepnet for Regression 4:16
Lecture 46 Implement a DNN with H2o For Multi-Class Supervised Classification 6:18
Lecture 47 Implement a (Less Intensive) DNN with H2o For Supervised Classification 3:59
Lecture 48 Implement a DNN With Keras 3:59
Lecture 49 Implement a DNN With Keras 8:48
Lecture 50 Identify Variable Importance 9:2
Lecture 51 Implement MXNET via caret
Lecture 52 Implement a DNN with H2o For Regression 3:51
Lecture 53 Implement a DNN with Keras For Regression
Lecture 54 Implement DNN Regression With Keras (Real Data) 8:40

Section 7 : Unsupervised Classification with Deep Learning

Lecture 55 Theory Behind Unsupervised Classification 1:39
Lecture 56 Autoencoders for Unsupervised Learning 1:46
Lecture 57 Autoencoders for Credit Card Fraud Detection 4:12
Lecture 58 Use the Autoencoder Model for Anomaly Detection 5:1
Lecture 59 Autoencoders for Unsupervised Classification 6:58
Lecture 60 Autoencoders With Keras 8:56
Lecture 61 Keras Autoencoders on Real Data 9:38
Lecture 62 Stacked Autoencoder With Keras 3:37
Lecture 63 Keras For Outlier Detection 4:33
Lecture 64 Find the Outlier 3:53
Lecture 65 Outlier Detection For Cancer (With Keras) 8:50

Section 8 : CNN Intuition

Lecture 66 Plan of Attack 3:32
Lecture 67 What are convolutional neural networks 15:49
Lecture 68 Step 1 - Convolution Operation 16:38
Lecture 69 Step 1(b) - ReLU Layer 6:41
Lecture 70 Step 2 - Pooling 14:13
Lecture 71 Step 3 - Flattening 1:53
Lecture 72 Step 4 - Full Connection 19:25
Lecture 73 Summary 4:20
Lecture 74 Softmax & Cross-Entropy 18:20

Section 9 : Practical CNN Implementation in R

Lecture 75 Implement a CNN for Multi-Class Supervised Classification 8:32
Lecture 76 More About Our CNN Model Accuracy 5:52
Lecture 77 Set Up CNN With Keras 5:3
Lecture 78 More About CNN With Keras 3:24
Lecture 79 Implement Keras CNN On Real Images 10:33
Lecture 80 Some More Explanations 2:49
Lecture 81 Improve CNN Performance 13:21

Section 10 : Working With Textual Data

Lecture 82 Basic Pre-Processing of Text Data 5:40
Lecture 83 Detect Frauds Using Keras Autoencoders on Text Data 10:25
Lecture 84 Word Embeddings For Classifying Fraud 10:39
Lecture 85 Word Embeddings For Classifying Fraud-GloVe 7:31