| Sln | Topic | Details | ||
| Module 1 - Primer | ||||
| 01 | Introduction to Machine Learning | What is Machine Learning Types of Learning (Supervised, Unsupervised, Reinforced) Structured vs Unstructured Data Applications of Machine Learning in Real Life | ||
| 02 | Math toolbox for ML | Linear Algebra Vector Algebra (Addition, Product, Projections) Matrix Algebra (Transpose, Multiplication, Inverse, Eigen Values) Optimization Maxima and Minima (calculus based) Lagrangian Multipliers Gradient Descent Parameter Estimation Maximum Likelihood Method (MLE) Maximum a Posteriori (MAP) | ||
| 03 | Getting Started with Python | Python basic data types - CRUD Numpy Python Plotting Pandas Probability & Stats in python Regression in Python. Time Series in Python Monte Carlo Simulations in Python | ||
| Module 2 – Predictive Analytics | ||||
| 04 | Linear Regression | Ways to estimate coefficients in Regression Model Simple vs Multiple Linear Regression Regression Assumptions (Multicollinearity, OVB, Serial Correlation, Hateroscedasticity) Stepwise regression | ||
| 05 | Types of Regression | Principal Component Regression MCMC Kalman Regression | ||
| 06 | Time Series Model | Checking Stationarity of Data Deterministic, Stochastic Trend & Seasonality Autocorrelation & Partial Autocorrelation Functions Fitting ARIMA models LSTM - Long Short Term Memory | ||
| Module 3 – Supervised Learning (Classification) | ||||
| 07 | Decision Boundary Algorithms | Linear Discriminant Analysis Linear SVM Non Linear SVM Kernel SVM | ||
| 08 | Logistic Regression | Logistic Regression | ||
| 09 | Decision Trees | Classification Trees Regression Trees Stooping & Pruning Criterias | ||
| 10 | KNN | Distance Measures K- Nearest Neighbour | ||
| 11 | Neural Networks | Gradient Descent Forward Propoagation Backward Propagation | ||
| 12 | Classification Model Selection and Performance | ROC & CAP Curve Confusion Matrices | ||
| Module 4 – Supervised Learning (Regression) | ||||
| 13 | Bias vs Variance Trade Off | K Fold Cross Validation | ||
| 14 | Regularisation techniques | Lasso Ridge Elastic Net | ||
| Module 5 – Unsupervised Learning | ||||
| 15 | Dimensionality Reduction | Principal Component Analysis (PCA) | ||
| 16 | Clustering | Hierarchical Clustering K-Means Clustering Partitive Clustering | ||
| Module 6 – Reinforcement Learning | ||||
| 17 | Markov Decision Proces | State, Action, Rewards Matrix | ||
| 18 | Model based Learning vs Model Free Learning | Analytical Solution Iterative Procedure Random Exploration & Exploitation Utility Based Method | ||
| 19 | On Policy Evaluation vs Off Policy Evaluation | Utility Based Method SARSA | ||
| Module 7 – Natural Language Processing (NLP) | ||||
| 20 | Data Preparation | Cleaning Regex | ||
| 21 | Data Wrangling | Tokenisation Normalisation Bag of Words n- Grams Lowercasing Stop words Stemming Document Term Matrix | ||
| 22 | Exploratory Data analysis | Term Frequency (Word Cloud) Document Frequency | ||
| 23 | Feature selection | Chi Sq Test Mutual Information | ||
| 24 | Feature Engineering | n-Grams POS Name entity recognition | ||
| 25 | Model Training & Validation | |||
