Vikram Sarabhai Memorial College
Vikram Sarabhai Centre for Advanced Technology
Certificate Programme in Machine Learning and Deep Learning
Certificate Programme in Machine Learning and Deep Learning
Machine Learning (ML) and Deep Learning (DL) algorithms have successfully been applied in many business areas, in order to make tasks more feasible, efficient, and precise than ever before. This in turn has surged the demand for professionals with new-age skills who could understand and fulfil the organisation’s demand better than competitors. IIT Delhi’s Certificate Programme in Machine Learning and Deep Learning course will future-proof your career by equipping you with in-demand ML & DL skills. With a comprehensive module, the programme will help you unlock new insights and value in your role.
Course Content
Module 1: Programming with Python
- Foundations of Python Programming
- Data Structures in Python, Loops, and Control Structures
- Functional Programming in Python
- Linear Algebra Using NumPy
- Data Pre-processing Using Pandas
- Data Visualisation using Matplotlib
- Scikit-learn
Module 2: Mathematical Foundations
- Linear Algebra: Vectors, Matrices, Norms, Subspaces, Projections, SVD, EVD, Derivatives of Matrices, Vector Derivative Identities, Least Squares
- Optimisation: Gradient Descent, Second Derivative Test, Constrained Optimisation, KKT
- Probability Theory: Discrete and Continuous Random Variables, Conditional Probability, Joint Probability Distribution, Multivariate, MAP Criterion, ML Criterion
Module 3: Machine Learning and Neural Networks
- Introduction to AI/ML/DL and Data Analysis
- Linear Regression Model
- Introduction: Supervised & Unsupervised Learning, Classification & Regression Models
- Bayesian Decision Theory: Bayesian Classifier, Discriminant Functions, Minimum Error Rate Classification
- Naïve Bayes Theory with Example
- Logistic Regression Model
- Parameter Estimation-Maximum Likelihood
- Principal Component Analysis
- Non-parametric Techniques: K-nearest Neighbor, Density Estimation
- Decision Tree with Example (Entropy, Gini Impurity Index)
- Perceptron, Multilayer Perceptron, LMS, Feedforward Operation, Backpropagation Algorithm, Activation Function, Loss Function, XOR Problem, Cross-validation, Regularisation, Demonstration on Classification and Regression Applications
- Radial Basis Functions and K-means Clustering
- Support Vector Machine (SVM)
- Random Forest, Ensemble Learning, Bagging, Boosting
Module 4: Deep Learning
- Basics of Deep Learning
- Deep Learning Architectures: DNN, CNN, RNN, LSTM, Autoencoder
- Methodology and Applications
- Demonstration of Deep Learning Applications
Module 5: Applications of Machine Learning
- Computer Vision
- Speech Recognition
- NLP