IISc Bangalore · Computer Science
Mathematical Foundations of Machine Learning
Prof. Prathosh A P · 85 free video lectures
85 video lectures. Topics: Overview of Function Approximation; Recap of Probability Theory - 1, Part 1; Recap of Probability Theory - 1, Part 2; Recap of Probability Theory - 1, Part 3; Recap of Probability Theory Part 2; Understanding a Chest X-Ray as Sample from Distribution; IID Assumption…
▶ Play on Open Lecture HallCourse page ↗
Lectures
- Overview of Function Approximation
- Recap of Probability Theory - 1, Part 1
- Recap of Probability Theory - 1, Part 2
- Recap of Probability Theory - 1, Part 3
- Recap of Probability Theory Part 2
- Understanding a Chest X-Ray as Sample from Distribution
- IID Assumption
- Distribution Estimation
- Density Function
- Challenge With ML
- Tutorial 1 : Introduction to Python Basics
- Tutorial 2 : Simple Problem solving in Probability Theory
- Entropy
- Kullback-Leibler (KL) Divergence
- Minimization of KL Divergence
- Example of ML Estimate
- Risk Minimization Framework
- Bayes Classifier
- Tutorial 3 : Risk Minimization Framework
- MLE for Gaussian Distribution
- MLE for Generalized Discrete Random Variable
- Density Estimation for Mixed Distribution
- Latent Variable Models
- MLE for Latent Variable Models
- Expectation Maximization Algorithm
- Tutorial 4 : Minmax Classifier
- Tutorial 5 : Neyman Pearson Classifier
- Tutorial 6 : Example of NP Classifier, ROC Curve
- Tutorial 7A : MLE for Gaussian Distribution
- Tutorial 7B : MLE for Generalized Discrete Distribution
- Convergence of EM
- EM for GMMs
- MAP Estimate
- Parzen Window
- Nearest Neighbor Classifier
- Tutorial 8 : Computation of EM for GMMs
- Tutorial 9 : MAP Estimate
- Ordinary Least Squares (OLS)
- Generalized Least Squares (GLS)
- Linear Models for Classification
- Bias - Variance Decomposition and Analysis
- Bias & Variance in Practice
- Tutorial 10 Part A : Numerical Example on Bayes Classifier
- Tutorial 10 Part B : Numerical Example on MLE and MAP Estimate
- Regularization
- Regularized ERM and MAP Estimate
- Stochastic Gradient Descent as a Regularizer
- Max-Margin Classifier and SVM
- SVM Formulation
- Dual Function in SVM
- SVM for Non-Linear Seperable Case
- SVM with Kernel Function
- Neural Networks and Universal Approximation Theorem
- ERM on Neural Networks and Error Backpropagation
- Local Receptive Field and Parameter Sharing
- Convolutional Neural Networks(CNNs) as Regularized MLP
- Recurrent Neural Networks(RNNs)
- Back Prapogation in RNNs and Vanishing Gradients Problem
- LSTMs and GRUs
- Tutorial 11 : Pytorch - Tensors and Data Loaders
- Tutorial 12 : Pytorch - Building MLP and Auto Grad
- Tutorial 13 : Pytorch - Training the Model
- Attention Part1
- Attention Part2
- Multi-Head Attention and Transformer Architecture
- Positional Embeddings
- Transfer Learning and Knowledge Distilation
- SGD, RMS Prop, ADAM : Optimizers
- Tutorial 14 Part 1 : CNNs
- Tutorial 14 Part 2 : Transfer Learning using CNNs
- Tutorial 15 Part 1 : RNNs, LSTMs and GRUs
- Tutorial 15 Part 2 : Deep RNNs, LSTMs and GRUs
- Decision Trees and Impurity Measures
- Regression Trees
- Ensemble Methods, Bagging and Boosting
- Gradient Boosting Algorithm
- Ada-Boosting
- Cross Validation
- Un-Supervised Learning
- K-Means Clustering
- PCA - Principal Component Analysis
- NCE - Noise Contrastive Estimation
- NCE, Info-NCE, SimCLR, JEPA
- Introduction to Generative Models
- GAN - Generative Adversarial Networks
From NPTEL (IITs and IISc) · CC BY-NC-SA. More from IISc Bangalore.
Open Lecture Hall is free, with no ads and no sign-up. It is not run by or connected to any university; the lectures are the universities' own free recordings, played from where they host them. About & rights