Machine Learning for Engineering & Science Applications | IIT Madras
Unlock the Future: Master AI & Machine Learning with NPTEL-IITM’s Comprehensive Course! Dive into Neural Networks, Deep Learning, Probabilities, and Optimization Techniques tailored for Engineering & Science Applications. Your AI journey starts here!
4.0
(2)
22 learners
What you'll learn
- Understand the historical development and foundational concepts of artificial intelligence.
- Gain proficiency in applying machine learning techniques to engineering and science problems.
- Develop skills in using linear algebra and calculus for machine learning modeling.
- Learn to implement and optimize machine learning algorithms using Python packages.
This course includes
- 32 hours of video
- Certificate of completion
- Access on mobile and TV
Course content
1 modules • 106 lessons • 32 hours of video
Comprehensive Guide to AI and Machine Learning Applications
106 lessons
• 32 hours
Comprehensive Guide to AI and Machine Learning Applications
106 lessons
• 32 hours
- #1 Introduction to the Course History of Artificial Intelligence 44:24
- #2 Overview of Machine Learning | Machine Learning for Engineering & Science Applications 31:12
- #3 Why Linear Algebra ? | Scalars, Vectors, Tensors 22:58
- #4 Basic Operations | Machine Learning for Engineering & Science Applications 14:01
- #5 Norms | Machine Learning for Engineering & Science Applications 16:38
- #6 Linear Combinations | Span Linear Independence 11:06
- #7 Matrix Operations Special Matrices Matrix Decompositions 35:47
- #8 Introduction to Probability Theory Discrete & Continuous Random Variables 26:51
- #9 Conditional | Joint | Marginal Probabilities Sum Rule & Product Rule Bayes' Theorem 26:01
- #10 Bayes' Theorem | Simple Examples | Machine Learning for Engineering & Science Applications 28:12
- #11 Independence Conditional Independence Chain Rule Of Probability 17:56
- #12 Expectation | Machine Learning for Engineering & Science Applications 16:18
- #13 Variance Covariance | Machine Learning for Engineering & Science Applications 26:05
- #14 Some Relations for Expectation & Covariance | Slightly Advanced 14:06
- #15 Machine Representation of Numbers | Overflow | Underflow | Condition Number 37:44
- #16 Derivatives | Gradient | Hessian | Jacobian | Taylor Series 21:33
- #17 Matrix Calculus | Slightly Advanced | Machine Learning for Engineering & Science Applications 16:55
- #18 Optimization | Part 1 | Unconstrained Optimization 12:35
- #19 Introduction to Constrained Optimization | Unconstrained Optimization 08:18
- #20 Introduction to Numerical Optimization Gradient Descent | Part 1 22:54
- #21 Gradient Descent | Part 2 | Proof | Numerical Gradient | Stopping Criteria 15:39
- #22 Introduction to Packages | Machine Learning for Engineering & Science Applications 16:06
- #23 The Learning Paradigm | Machine Learning for Engineering & Science Applications 26:15
- #24 A Linear Regression Example | Machine Learning for Engineering & Science Applications 11:00
- #25 Linear Regression | Least Squares | Gradient Descent 21:52
- #26 Coding Linear Regression | Machine Learning for Engineering & Science Applications 11:42
- #27 Generalized Function for Linear Regression 16:43
- #28 Goodness of Fit | Machine Learning for Engineering & Science Applications 10:46
- #29 Bias Variance Trade Off | Machine Learning for Engineering & Science Applications 26:18
- #30 Gradient Descent Algorithms | Machine Learning for Engineering & Science Applications 12:05
- #31 Introduction to Week 5 | Deep Learning | Machine Learning for Engineering & Science Applications 12:31
- #32 Logistic Regression | Machine Learning for Engineering & Science Applications 12:15
- #33 Binary Entropy Cost Function | Machine Learning for Engineering & Science Applications 12:53
- #34 OR Gate Via Classification | Machine Learning for Engineering & Science Applications 10:59
- #35 NOR | AND | NAND Gates | Machine Learning for Engineering & Science Applications 05:36
- #36 XOR Gate | Machine Learning for Engineering & Science Applications 19:32
- #37 Differentiating the Sigmoid | Machine Learning for Engineering & Science Applications 02:19
- #38 Gradient of Logistic Regression | Machine Learning for Engineering & Science Applications 24:35
- #39 Code for Logistic Regression | Machine Learning for Engineering & Science Applications 05:40
- #40 Multinomial Classification | Introduction 04:30
- #41 Multinomial Classification | One Hot Vector 06:11
- #42 Multinomial Classification | Softmax | Machine Learning for Engineering & Science Applications 17:29
- #43 Schematic of Multinomial Logistic Regression 08:28
- #44 Biological Neuron | Machine Learning for Engineering & Science Applications 07:50
- #45 Structure of an Artificial Neuron | Machine Learning for Engineering & Science Applications 04:54
- #46 Feedforward Neural Network | Machine Learning for Engineering & Science Applications 08:28
- #47 Introduction to Back Prop | Machine Learning for Engineering & Science Applications 38:13
- #48 Summary of Week 05 | Machine Learning for Engineering & Science Applications 10:39
- #49 Introduction to Convolution Neural Networks (CNN) 51:25
- #50 Types of Convolution | Machine Learning for Engineering & Science Applications 13:22
- #51 CNN Architecture | Part 1 | LeNet & Alex Net 21:08
- #52 CNN Architecture | Part 2 | VGG Net | Machine Learning for Engineering & Science Applications 10:44
- #53 CNN Architecture | Part 3 | GoogleNet | Machine Learning for Engineering & Science Applications 19:51
- #54 CNN Architecture | Part 4 | ResNet | Machine Learning for Engineering & Science Applications 12:36
- #55 CNN Architecture | Part 5 | DenseNet | Machine Learning for Engineering & Science Applications 17:17
- #56 Train Network for Image Classification | Machine Learning for Engineering & Science Applications 22:46
- #57 Semantic Segmentation | Machine Learning for Engineering & Science Applications 34:11
- #58 Hyperparameter Optimization | Machine Learning for Engineering & Science Applications 11:42
- #59 Transfer Learning | Machine Learning for Engineering & Science Applications 16:16
- #60 Segmentation of Brain Tumors from MRI using Deep Learning 38:51
- #61 Activation Functions | Machine Learning for Engineering & Science Applications 07:49
- #62 Learning Rate Decay | Weight Initialization 15:36
- #63 Data Normalization | Machine Learning for Engineering & Science Applications 11:59
- #64 Batch Norm | Machine Learning for Engineering & Science Applications 16:27
- #65 Introduction to RNNs | Machine Learning for Engineering & Science Applications 39:12
- #66 Example | Sequence Classification | Machine Learning for Engineering & Science Applications 33:14
- #67 Training RNNs | Loss & BPTT | Machine Learning for Engineering & Science Applications 29:41
- #68 Vanishing Gradients & TBPTT | Machine Learning for Engineering & Science Applications 25:37
- #69 RNN Architectures | Machine Learning for Engineering & Science Applications 30:01
- #70 LSTM | Machine Learning for Engineering & Science Applications 13:25
- #71 Why LSTM Works? | Machine Learning for Engineering & Science Applications 05:29
- #72 Deep RNNs & Bi RNNs | Machine Learning for Engineering & Science Applications 14:20
- #73 Summary of RNNs | Machine Learning for Engineering & Science Applications 04:16
- #74 Introduction | Machine Learning for Engineering & Science Applications 02:27
- #75 Knn | Machine Learning for Engineering & Science Applications 10:58
- #76 Binary Decision Trees | Machine Learning for Engineering & Science Applications 25:28
- #77 Binary Regression Trees | Machine Learning for Engineering & Science Applications 15:23
- #78 Bagging | Machine Learning for Engineering & Science Applications 22:17
- #79 Random Forest | Machine Learning for Engineering & Science Applications 06:41
- #80 Boosting | Machine Learning for Engineering & Science Applications 34:05
- #81 Gradient Boosting | Machine Learning for Engineering & Science Applications 18:38
- #82 Unsupervised Learning & Kmeans | Machine Learning for Engineering & Science Applications 25:32
- #83 Agglomerative Clustering | Machine Learning for Engineering & Science Applications 18:33
- #84 Probability Distributions | Gaussian | Bernoulli 32:06
- #85 Covariance Matrix of Gaussian Distribution 03:41
- #86 Central Limit Theorem | Machine Learning for Engineering & Science Applications 04:09
- #87 Naive Bayes | Machine Learning for Engineering & Science Applications 28:36
- #88 MLE Intro | Machine Learning for Engineering & Science Applications 09:21
- #89 PCA | Part 1 | Machine Learning for Engineering & Science Applications 04:20
- #90 PCA | Part 2 | Machine Learning for Engineering & Science Applications 10:12
- #91 Support Vector Machines | Machine Learning for Engineering & Science Applications 16:42
- #92 MLE | MAP & Bayesian Regression | Machine Learning for Engineering & Science Applications 24:45
- #93 Introduction to Generative Model | Machine Learning for Engineering & Science Applications 20:15
- #94 Generative Adversarial Networks (GAN) | Machine Learning for Engineering & Science Applications 28:45
- #95 Variational Auto Encoders (VAE) | Machine Learning for Engineering & Science Applications 29:32
- #96 Applications | Cardiac MRI | Segmentation & Diagnosis 37:09
- #97 Applications | Cardiac MRI Analysis | Tensorflow Code Walkthrough 22:55
- #98 Introduction to Week 12 | Machine Learning for Engineering & Science Applications 10:31
- #99 Application | Part 1 | Description | Fin Heat Transfer 10:49
- #100 Application | Part 1 | Solution | Description | Fin Heat Transfer 14:15
- #101 Application | Part 2 | Description | Computational Fluid Dynamics 15:32
- #102 Application | Part 2 | Solution | Machine Learning for Engineering & Science Applications 23:25
- #103 Application | Part 3 | Description | Topology Optimization 04:31
- #104 Application | Part 3 | Solution | Machine Learning for Engineering & Science Applications 07:15
- #105 Application | Part 4 | Solution of PDE/ODE using Neural Networks 30:57
- #106 Summary & Road Ahead | Machine Learning for Engineering & Science Applications 14:26
Related learning topics
Take this course with you
Download the app to continue lessons from your phone anytime.
