o Link for ISLR
o Supervised Learning Overview
o Evaluating Performance – Classification
o Evaluating Performance – Regression Error
o Machine Learning with Python
o Bias-Variance Trade-Off
o Over-fitting and Under-fitting
o Leave-p-out Cross-Validation(LpOCV)
o Leave-One-out Cross-Validation(LOOCV)
o K-fold Cross-Validation
o Max Voting
o Averaging
o Weighted Average
o Bootstrap Aggregation(Bagging)
o Boosting

o Optimization
o Maxima and Minima
o Steps to find Maxima and minima
o Saddle point
o Cost function (Loss Function)
o Optimization Strategies
o Learning Rate and Its Importance
o Optimization Strategies-Gradient Descent
o Step to Calculate Gradient Descents
o Identifying Gradient Descents performance
o Gradient Descents for Machine Learning
o Procedure for Batch Gradient Descent
o Procedure for Stochastic Gradient Descent
o Difference Between Batch and Stochastic Gradient Descent
o Disadvantage of Gradient Descent
o Momentum
o Nesterov Accelerated Gradient
o Adaptive Gradient Procedure-Adagrad
o Advantage and Disadvantage of Adagrad
o Root Mean Squared Propagation-RMSprop
o Adaptive Moment Estimation Procedure-ADAM

o Introduction
o Modelling Process
o Data Representation
o Feature Extraction
o Estimator API
o Conventions
o Linear Modeling
o Extended Linear Modeling
o Stochastic Gradient Descent
o Support Vector Machines
o Anomaly Detection
o K-Nearest Neighbors
o KNN Learning
o Classification with Naïve Bayes
o Decision Trees
o Randomized Decision Trees
o Boosting Methods
o Clustering Methods
o Clustering Method Evaluation
o Principal Component Analysis
o Dimensionality Reduction using PCA
o Algorithms
n Linear Regression
n Logistic Regression
n Support Vector Machine
n Naïve Bayes (Gaussian)
n SGD
n KNN
n Decision Tree
n Random Forest
n Gradient Boosting
n Xgboost
n K- Means Clustering
n Apriori

o Whats is Machine learning
o Machine Learning Basic
o Types of Learning
o Problem Types
o Challenges Motivating Deep Learning
o Deep Learning(DL)
o History of Deep Learning
o Applications of Deep learning
o Need for Deep Learning?
o Why Deep learning is called ‘Deep’?
o Misconceptions about Deep Learning
o Deep Learning Architecture
o What is Artificial Neural Networks?
o Perceptrons
o Simple Neuron /Node
o How does it work?
o Deep Learning Neural Network
o Gradient Descent
o Non-Linear Activation Function
o What if Linear Activation Function
o Deep Auto-encoders
o Drop out
o Improving DNN Performance
o Deep Learning Libraries

1. Iris Flowers Classification
2. Cartoonify Image
3. Loan Default Prediction
4. Real Estate Price Prediction
5. Stock Price Prediction
6. Titanic Survival Classification
7. Twitter Sentiment Analysis by tweepy

1. Human Face Detection
2. Image Classification with CIFAR-10
3. Breast Cancer Classification
4. Music Genre Classification
5. Chatbot using Deep Learning
6. Image Caption Generation
7. Coloring Old B &W Images