Overview Metallurgy and Material Science course by Prof. Krishanu Biswas, Prof. Pratik Kumar Ray.
Syllabus 12 Week 1 Lecture 1(A) : General Introduction (Part 1) Lecture 1(B) : General Introduction (Part 2) Lecture 2(A) : Statistics & Regression (Part 1) Lecture 2(B) : Statistics & Regression (Part 2) Lecture 3(A) : Probability & Classification (Part 1) Week 2 Lecture 3(B) : (Part - 2) Probability & Classification Lecture 4(A) : (Part-1) Data Handling - I Lecture 4(B) : (Part-2) Data Handling - I Lecture 5(A) : (Part-1) Data Handling - II Lecture 5(B) : (Part-2) Data Handling - II Week 3 Lecture 6(A) : Materials Informatics in Action (Part - 1) Lecture 6(B) : Materials Informatics in Action (Part - 2) Lecture 7(A) : The Gradient Descent Methods (Part - 1) Lecture 7(B) : The Gradient Descent Methods (Part - 2) Lecture 8(A) : Regularization and solvers in regression Week 4 Lecture 8(B) : Regularization and solvers in regression Lecture 9(A) : Various Types of Machine Learning (Part-1) Lecture 9(B) : Various Types of Machine Learning (Part-2) Lecture 10(A) : Describing the Problems (Part-1) Lecture 10(B) : Describing the Problems (Part-2) Week 5 L11(A) : Linear Models (Part-1) L11(B) : Linear Models (Part-2) L12(A) : Decisions Tree (Part-1) L12(B) : Decisions Tree (Part-2) L13(A) : Decision Trees (Part-1) Week 6 Lecture 13(B) : Support Vector Machine (part - 2) Lecture 14(A) : Support Vector Machine (part -1) Lecture 14(B) : Support Vector Machine and Neural Networks (part - 2) Lecture 15(A) : Neural Networks (part -1) Lecture 15(B) : Neural Networks (part - 2) Week 7 Lecture 16(A) : Clustering (Part - 1) Lecture 16(B) : Clustering (Part - 2) Lecture 17(A) : Model Selection (Part - 1) Lecture 17(B) : Clustering (Part - 2) Lecture 18(A) : Visualization (Part - 1) Lecture 18(B) : Visualization and transformation (Part - 2) Week 8 Lecture 19(A) - (part 1): Dataset transformations Lecture 19(B) - (part 2): Dataset transformations Lecture 20(A) - (part 1): Data mining Lecture 20(B) - (part 2): Mapping of materials Lecture 21(A) - (part 1) : Data in Materials Informatics Lecture 21(B) - (part 2) : Data in Materials Informatics Lecture 22(A) _ (part 1) : Structure Maps Lecture 22(B) - (part 2) : Structure Maps Week 9 Lecture -23 (Part 1) - Phase Diagrams Lecture -23 (Part 2) - Periodic Table and Elemental Descriptors Lecture -24 (Part 1) - Featurization - Physical Principles Lecture -24 (Part 2) - Featurization - Pair Plots and Correlation Matrix Lecture 25 - Thermodynamic Features - Miedema’s Model Lecture 26 - ( part 1) : Structure of Materials Week 10 Lecture -26 (part 2): Structure of Materials - Microstructure Lecture -27 (part 1): Prediction of Composition Based Properties - I Lecture -27 (part 2): Prediction of Composition Based Properties - II Lec-28 (part 1): Molecular Fingerprints - I Lec-28 (part 2): Molecular Fingerprints - II Lecture -29 (part 1): Mathematical Microstructure Lecture -29 (part 2): The Microstructure Function Week 11 Lecture 30 - Two-point Statistics and Dimensionality Reduction Lecture 31 A - Combinatorial-Materials-Science Lecture 31 B - Convolutional Neural Network Lecture 32 - Microstructure Representation-Synthetic Microstructures Lecture 33 - P-S-P Linkage Lecture 34 - Decision Making and Interpretation Week 12 Lecture 35 Part 1: (Setting up ML problems) Lecture 35 Part 2: (Interrogating Machine Learning models - Examples) Lecture 36: (Physically Informed Neural Networks) Lecture 37: (Combinatorial Materials Processing) Lecture 38: (High throughput Characterization) Lecture 39: (Synthetic Data) Lecture 40: (Conclusion, Challenges and Future Directions) Advantages and disadvantages Taught by IIT and IISc professors, and it follows the Indian university syllabus closely. All videos and assignments are free on NPTEL and SWAYAM. The certificate is recognised by many Indian universities for credit transfer and by GATE aspirants. Great for GATE and semester exam preparation. Completely free. Self-paced: start any time. A clear syllabus (12 parts) you can see before you start. The certificate needs a proctored exam at a centre, which has a fee. Recorded classroom lectures: thorough, but slower than made-for-online courses. New runs start on fixed dates (January and July). Learning is free, but the certificate costs money. Some points apply to every course of this kind; see how we rank .
Free: Every video and assignment is free on NPTEL and SWAYAM. Enrol when the next run opens.Certificate: Optional. It needs a proctored exam at a centre, which has a fee.Taught by Prof. Krishanu Biswas, Prof. Pratik Kumar Ray IIT Kanpur / IIT Ropar 
