Topic 1 Overview of Machine Learning and Scikit Learn 

• Introduction to Machine Learning 
• Supervised vs Unsupervised Learnings 
• Machine Learning Applications and Case Studies 
• What is Scikit Learn 
• Installing Scikit-Learn 

Topic 2 Classification 

• What is Classification 
• Classification Algorithms 
• Classification Workflow 
• Confusion Matrix 
• Binary Classification Metrics 
• ROC and AUC 

Topic 3 Regression 

• What is Regression? 
• Regression Algorithms 
• Regression Workflow 
• Regression Metrics 
• Overfitting and Regularizations 

Topic 4 Clustering 

• What is Clustering 
• K-Means Clustering 
• Silhouette Analysis 
• Dendrogram and Hierarchical Clustering 

Topic 5 Principal Component Analysis 

• Curse of Dimensionality Issue 
• What is Principal Component Analysis (PCA) 
• Feature Reduction with PCA 

Day 1 

Topic 1 Overview of Machine Learning & Tensorflow 2.x 

• Overview of Machine Learning and Deep Learning 
• Introduction to Tensorflow 2.x 
• Install Tensorflow 2.x 

Topic 2 Basic Tensorflow Operations 

• Basic Tensor Data Types 
• Constant, Variable & Gradient 
• Matrix Operations 
• Eagle Mode vs Graph Mode 

Topic 3 Datasets 

• MNIST Handwritten Digits and Fashion Datasets 
• CIFAR Image Dataset 
• IMDB Text Dataset 

Topic 4 Neural Network for Regression 

• Introduction to Neural Network (NN) 
• Activation Function 
• Loss Function and Optimizer 
• Machine Learning Methodology 
• Build a NN Predictive Regression Model 
• Load and Save Model 

Topic 5 Neural Network for Classification 

• Softmax 
• Cross Entropy Loss Function 
• Build a NN Classification Model 

Topic 6 Convolutional Neural Network (CNN) 

• Introduction to Convolutional Neural Network (CNN) 
• Convolution & Pooling 
• Build a CNN Model for Image Recognition 
• Overfitting and Underfitting Issues 
• Methods to Solve Overfitting 
• Small Dataset Overfitting Issue 
• Data Augmentation & Dropout 

Topic 7 Recurrent Neural Network (RNN) 

• Introduction to Recurrent Neural Network (RNN) 
• Types of RNN Architectures 
• LSTM and GRU 
• Word Embedding 
• Build a RNN Model for Text Classification