| Event Type | Date | Description | Readings | Course Materials |
|---|---|---|---|---|
| Lecture 1 | Thursday Jan 02 |
Introduction Course logistics and overview. |
[slides (pptx)] | |
| Lecture 2 | Friday Jan 03 |
Linear Algebra Review Brief review of concepts from Linear Algebra. |
[slides (pptx)] | |
| Lecture 3 | Wednesday Jan 08 |
Optimization Types of errors, bias-variance trade-off, overfitting-underfitting, brief review of concepts from Vector Calculus and optimization, variants of gradient descent, momentum. |
[slides (pptx)] | |
| Lecture 4 | Thursday Jan 09 |
|||
| Lecture 5 | Friday Jan 10 |
|||
| Lecture 6 | Wednesday Jan 15 |
|||
| Lecture 7 | Friday Jan 17 |
|||
| Lecture 8 | Wednesday Jan 22 |
Logistic Regression Basic concepts of rgression and classification problems, linear models addressing regression and classification, maximum likelihood, logistic regression classifiers. |
[slides (pdf)] | |
| Lecture 9 | Thursday Jan 23 |
|||
| Lecture 10 | Friday Jan 24 |
|||
| Lecture 11 | Thursday Jan 30 |
Neural Networks Basic concepts of artificial neurons, single and multi layer perceptrons, perceptron learning algorithm, its convergence proof, different activation functions, softmax cross entropy loss function. |
[slides (pptx)] | |
| Lecture 12 | Friday Jan 31 |
|||
| Lecture 13 | Wednesday Feb 05 |
|||
| Lecture 14 | Thursday Feb 06 |
ConvNets Basic concepts of Convolutional Neural Networks starting from filetering. Convolution and pooling operation and arithmatics of these. |
[slides (pptx)] | |
| Lecture 15 | Friday Feb 07 |
|||
| Lecture 16 | Wednesday Feb 12 |
ConvNet Architectures Discussions on famous convnet architectures - AlexNet, ZFNet, VGG, C3D, GoogLeNet, ResNet, MobileNet-v1. |
[slides (pdf)] | |
| Lecture 17 | Thursday Feb 13 |
|||
| Lecture 18 | Friday Feb 14 |
|||
| Lecture 19 | Thursday Feb 27 |
Regularization, Batchnorm Discussion on regularization, Dropout, Batchnorm etc. |
[slides (pptx)] | |
| Lecture 20 | Thursday Feb 28 |
Detection, Segmentation (Part I) Discussion on detection, segmentation problem definition, challenges, Evaluation, Datasets and Localization by regression. |
[slides (pdf)] | |
| Lecture 21 | Wednesday Mar 04 |
Detection, Segmentation (Part II) Discussion on detection as classificaion, region proposals, RCNN architectures. |
[slides (pdf)] | |
| Lecture 22 | Thursday Mar 05 |
|||
| Lecture 23 | Wednesday Mar 11 |
Recurrent Neural Networks Discussion on Recurrent Neural Networks (RNNs), Long-Short Term Memory (LSTM) architectures and basics of word embedding. |
[slides (pdf)] [slides (pptx)] | |
| Lecture 24 | Thursday Mar 12 |
|||
| Lecture 25 | Thursday Mar 19 |
Vision and Language Discussion on different tasks involving Vision and Language e.g., Image and video captioning along with the use of attention. |
[slides (pdf)] | |
| Lecture 26 | Friday Mar 26 |
|||
| Lecture 27 | Wednesday Apr 01 |
Explainability and Bias Discussion on explainability and bias in Deep Learning system. The need for explanation, introspection vs justification, activation maximization and activation map based explanation generation, Black-box explanation generation etc. Bias in AI and in image captioning task. |
[slides (pptx)] | |
| Lecture 28 | Thursday Apr 02 |
|||
| Lecture 29 | Thursday Apr 03 |