Learn · Deep Learning in Material Science and Engineering: From Concepts to Applications
Lecture 24 of 65Week 6
Lecture 12: Part 1: Explainable AI, Saliency Maps & Visualization
Prof. Krishanu Biswas · IIT Kanpur
Credits and licence
- From
- Deep Learning in Material Science and Engineering: From Concepts to Applications, IIT Kanpur (at NPTEL)
- Licence
- CC BY-NC-SA, as NPTEL states it. Non-commercial use only.
- Attribution
- NPTEL states: "Distributed under Creative Commons Attribution-ShareAlike / CC BY - NC - SA", beside a BY-NC-SA badge.
- Who can watch
- Tweens profiles and older. How courses are placed
All the lectures
- Lecture 01 : Part 1 Introduction to Course and Deep Learning
- Lecture 01 : Part 2 Introduction to Course and Deep Learning
- Lecture 02 : Part 1 Foundation - Neural Network
- Lecture 02 : Part 2 Foundation - Neural Network
- Lecture-03: Part 1 (Artificial Neural Network : Basics)
- Lecture-03: Part 2 (Artificial Neural Network : Basics)
- Lecture-04: Part 1 (Convolution Neural Network)
- Lecture-04: Part 2 (Convolution Neural Network)
- Lecture 5 : Part 1: ANN- Backpropagation
- Lecture 5: Part 2: ANN- Backpropagation and Optimization
- Lecture 6: Part 1: CNN : Basic Concepts
- Lecture 6: Part 2: CNN : Gradient Descent Algorithm
- Lecture 07: Part 1: The Convolution Operation
- Lecture 07: Part 2: Kernels and Feature Extraction - I
- Lecture 08: Part 1: Feature Extraction - II
- Lecture 08: Part 2: CNN Architecture - I
- Lecture 09: Part 1 - CNN Architecture
- Lecture 09: Part 2 - Advancement in CNN
- Supplementary Lecture - Application of CNN in Materials Science a case study
- Lecture 10: Part 1 - Explainable AI basics
- Lecture 10: Part 2 - Explainable AI Fundamentals
- Lecture 11: Part 1: Explainable AI, basic concepts
- Lecture 11: Part 2: Explainable AI, domain and types
- Lecture 12: Part 1: Explainable AI, Saliency Maps & Visualization
- Lecture 12: Part 2: Explainable AI, Attrition based
- Lecture 13: Part 1: Explainable AI, Activation and Perturbation
- Lecture 13: Part 2: Image Segmentation and Classification- Part 1
- Supplementary Lec. - The fundamentals of neural networks and case studies of NN in Materials Science
- Lecture 14: Part 1: Image Segmentation and Object Detection, Types
- Lecture 14: Part 2: Image Segmentation and Object Detection. More on types
- Lecture 15: Part 1: Image Segmentation and Object Detection RCNN
- Lecture 15: Part 2: Image Segmentation and Object Detection, Faster RCNN
- Lecture 16: Part 1: Image Segmenttation ad Object Detection, YOLO
- Lecture 16: Part 2: Image Segmentation and Object Detection, more on YOLO
- Lecture 17: Part1- More on YOLO
- Lecture 17: Part 2 - U-Net: Introduction
- Lecture 18 - Part 1: U-Net and LSTM
- Lecture 18 - Part 2: LSTM further
- Lecture 19 - Part 1: More on LSTM
- Lecture 19 - Part 2: Further details on LSTM
- Supplementary Lecture
- Lecture 20 - Part 1: RNN- more details
- Lecture 20 - Part 2: LSTM and GRU
- Lecture 21 - Part 1: Natural Language Processing, basic concepts- I
- Lecture 21 - Part 2: Natural Language Processing, basic concepts- II
- Lecture 22 - Part 1: Natural Language Processing, Algorithms- I
- Lecture 22 - Part 2: Natural Language Processing- Word Embeddings-I
- Lecture 23: Part 1 - NLP- basics
- Lecture 23: Part 2 - Word2Vec and GLove
- Lecture 24: Part 1 - More on Word2Vec and GLove
- Lecture 24: Part 2 - Language Models
- Lecture 25: Part 1 - More on Language Models
- Lecture 25: Part 2 - LLMs- basic concepts
- Lecture 26 - Part 1: NLP- Self Attention -I
- Lecture 26 - Part 2: NLP- Self Attention-II
- Lecture 27 - Part 1: NLP- Self Attention-III
- Lecture 27 - Part 2: Autoencoder- Introduction
- Lecture 28 - Part 1: Autoencoder- More details
- Lecture 28 - Part 2: Autoencoder: Architecture
- Supplementary Lecture - Application of NLP :
- Lecture 29: Part 1 - Autoencoder - more on basics
- Lecture 29: Part 2 - Autoencoder - Types
- Lecture 30: Part 1 - In context learning - Reinforcement Learning - Fine tuning
- Lecture 30: Part 2 - In context learning - Diffusion Modeling and Epilogue
- Supplementary Lecture - Use of Autoencoder in Materials Science and Engineering