Syllabus

Introduction to Machine Learning: Supervised vs. Unsupervised Learning, Regression and Classification problems, Generalization, Underfitting, and Overfitting, Model evaluation: Bias-Variance trade-off, Cross-validation, Metrics (Accuracy, Precision, Recall, F1-score, RMSE, Coefficient of Determination, MAPE etc.

Supervised Learning Algorithms: Linear Regression, Polynomial Regression, Logistic Regression, k-Nearest Neighbors (k-NN), Decision Trees and Random Forests, Support Vector Machines (SVMs).

Neural Networks and Deep Learning Basics: Biological inspiration and Perceptrons, Multilayer Perceptrons (MLP), Activation functions, Loss functions, Backpropagation and Gradient Descent, Deep Learning Architectures: Deep Neural Networks, Convolutional Neural Networks (CNNs) Training Deep Neural Networks: Optimization techniques: SGD, Adam, RMSProp. Batch Normalization, Dropout, Weight Initialization, Overfitting and regularization techniques.

Unsupervised Learning: Clustering: k-Means, Dimensionality Reduction: PCA. Specialized Topics and Applications: Introduction to Physics-Informed Neural Networks (PINNs) and Transfer Learning, Applications in Healthcare, Finance, Scientific Computing etc.

To introduce the fundamental concepts and mathematical foundations of machine learning and deep learning.

To understand and implement classical ML algorithms and deep learning architectures.

To explore applications in areas such as Solving Partial Differential Equations, Biomedical Applications, Finance and Economics, and scientific computing.

To introduce the working procedure of the tools and frameworks like Scikit- learn, Pandas, Numpy, TensorFlow, and PyTorch.

Understand fundamental concepts of machine learning, including types of learning, hypothesis space, inductive bias, and model evaluation.

Apply and evaluate regression and classification algorithms to predict outputs from input data.

Analyze dimensionality reduction and feature extraction techniques to improve model performance.

Design specialized neural network models for solving partial differential equations (PDEs), as well as problems in finance, economics, and scientific computing.

Zhi-Hua Zhou, Machine Learning, Springer Singapore , https://doi.org/10.1007/978-981-15-1967-3

Kevin P. Murphy, Machine Learning: A Probabilistic Perspective, The MIT Press

Christopher M. Bishop, Pattern Recognition and Machine Learning, Springer New York, NY , ISBN 978-0-387-31073-2

Snehashish Chakraverty, Arup Kumar Sahoo, Dhabaleswar Mohapatra, Artificial Neural Networks and Type-2 Fuzzy Set, Elsevier

Ian Goodfellow, Yoshua Bengio, Aaron Courville, Deep Learning, MIT Press

IEEE Transaction on Neural Networks & Learning Systems

Applications of Physics-Informed Neural Networks in Power Systems - A Review