Subject Code: ML5L0XX Name: Introduction to Machine Learning for Engineers L-T-P: 3-1-0 Credit: 4
Pre-Requisites: Engineering Mathematics (Mathematics – I and II in B. Tech. curriculum of IITBBS) or equivalent ; Introduction to Programming and Data Structures, or equivalent
Objectives
  1. Familiarize the students with basics of probability and statics required for machine learning
  2. Familiarize the students with Machine Learning methods to address data-driven scientific understanding
  3. Equip the students with the basic tools of the emerging area
  4. Introduce the students with deep learning techniques
  5. Since engineering is all about materials embodiment of scientific principles, we introduce two very essential computational materials tools to engineers that has very high potential to be coupled with machine learning for engineering purposes
Suggested syllabus

Module-1 Machine Learning: Fundamental aspects of probability and statistics for machine learning. k- Nearest Neighbours (kNN), Decision trees and random forest, Singular value decomposition (SVD), Dimensionality reduction and Principal Component Analysis (PCA), Independent Component Analysis (ICA), Artificial and convolutional Neural Networks (ANN & CNN). Deep neural networks and their applications.

Module-2 (Two very essential computational materials tools to engineers that have very high potential to be coupled with machine learning for engineering purposes): Finite Element method and Discrete Element method.

The above modules will include case studies such as:

  1. Optimizing process parameters for battery fabrication and analysis of feature importance
  2. Retrieving original images (or audios) from corrupted images (or audios) demonstrating an example of digital forensics
  3. Crystal graph based CNN (CGCNN) for accelerated materials discovery
  4. 4. Identifying lung cancer nodules from CT scans
  5. Predicting temperature gradients in granular assemblies.
Suggested Books
  1. Python Machine Learning - Third Edition: Machine Learning and Deep Learning with Python, scikit-learn, and TensorFlow 2, Packt Publishing Limited, 2019
  2. Christopher M. Bishop; Pattern Recognition and Machine Learning; Springer 2006
  3. Richard Lesser, Introduction to Computational Materials Science, Cambridge Uni Press, 2016
Texts/Reference Books
  1. Deep Learning (Adaptive Computation and Machine Learning series); MIT Press, 2019.
  2. Kevin P. Murphy, Francis Bach; Machine Learning – A Probabilistic Perspective; MIT press, 2012
  3. Ellad B. Tadmor, Ronald E. Miller, Modeling Materials: Continuum, Atomistic and Multiscale techniques, Cambridge University Press, 2011
  4. Koenraad G. F. Janssens, Computational materials engineering : an introduction to microstructure evolution, Elsevier, Amsterdam, 2007
  5. D. C. Rapaport, The art of molecular dynamics simulation, Cambridge Uni Press 2010
  6. June Gunn Lee, Computational Materials Science: An Introduction, CRC Press 2012
  7. Robert Davis Cook, Concepts and applications of finite element analysis 2010
  8. Jacob Fish, Ted Belytschko, A First Course in Finite Elements, John Wiley & Sons 2007