Schedule and Syllabus


This course meets Wednesdays (11:00am-11:55am), Thursdays (12:00-12:55pm) and Fridays (08:00-09:00am)
Module 01 Lecture 1 Wednesday
Jan 05		 Introduction
Course logistics and overview. 		[slides (pptx)] [Link]
Lecture 2 Thursday
Jan 06		 Linear Algebra Primer, Vector Calculus Review
Brief review of concepts from Linear Algebra and Vector Calculus. 		[slides (pptx)] [Link]
Lecture 3 Friday
Jan 07		 Optimization
Types of errors, bias-variance trade-off, overfitting-underfitting, brief review of concepts from optimization, variants of gradient descent, momentum based methods. 		[slides (pptx)] [Link]
Lecture 4 Wednesday
Jan 12		 [Link]
Lecture 5 Thursday
Jan 13		 [Link]
Lecture 6 Friday
Jan 14		 [Link]
Module 02 Lecture 7 Wednesday
Jan 19		 Linear and Logistic Regression
Basic concepts of Linear and Logistic Regression. 		[slides (pdf)] [Link]
Lecture 8 Thursday
Jan 20		 [Link]
Module 03 Lecture 9 Friday
Jan 21		 Artificial 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)] [Link]
Lecture 10 Thursday
Jan 27		 [Link]
Class test-I on Module 01 and 02 on Jan 28 (Friday)
Module 04 Lecture 11 Wednesday
Feb 02		 ConvNets, ConvNet Architectures and Dropout/Regularization/Batchnorm
ConvNets: Basic concepts of Convolutional Neural Networks starting from filetering. Convolution and pooling operation and arithmatics of these. ConvNet Architectures: Discussions on famous convnet architectures - AlexNet, ZFNet, VGG, C3D, GoogLeNet, ResNet, MobileNet-v1, MobileNet-v2, EfficientNet, GhostNet.
Discussion on regularization, Dropout, Batchnorm etc. 		[slides (pptx)]
[slides (pdf)]
[slides (pptx)] 		[Link]
Lecture 12 Thursday
Feb 03		 [Link]
Lecture 13 Friday
Feb 04		 [Link]
Lecture 14 Wednesday
Feb 09		 [Link]
Lecture 15 Thursday
Feb 10		 [Link]
Lecture 16 Friday
Feb 11		 [Link]
Lecture 17 Friday
Feb 16		 [Link]
Class test-II on Module 01-04 on Feb 24 (Thursday)
Module 05 Lecture 18 Friday
Feb 18		 Applications: Detection and Segmentation
Discussion on detection, segmentation problem definition, challenges, Evaluation, Datasets and Localization by regression. Discussion on detection as classificaion, region proposals, RCNN and YOLO architectures, fully convolutional segmentations, Mask-RCNNs. 		[slides (pdf)]
[slides (pdf)] 		[Link]
Lecture 19 Saturday
Feb 19		 [Link]
Lecture 20 Wednesday
Mar 02		 [Link]
Lecture 21 Thursday
Mar 03		 [Link]
Lecture 22 Thursday
Mar 09		 [Link]
Lecture 23 Thursday
Mar 10		 [Link]
Lecture 24 Wednesday
Mar 16		 [Link]
Module 06 Lecture 25 Thursday
Mar 17		 Recurrent Architectures, Transformers, NLP Applications, Vision Transformers
Discussion on Recurrent Neural Networks (RNNs), Long-Short Term Memory (LSTM) architectures. 		[slides (pdf)]
 [Link]
Lecture 26 Saturday
Mar 19		 [Link]
Lecture 27 Wednesday
Mar 23		 Discussion on Attention, Transformers. [slides (pdf)] [Link]
Lecture 28 Thursday
Mar 24		 [Link]
Lecture 29 Saturday
Mar 26		 [Link]
Lecture 30 Wednesday
Mar 30		 Discussion on NLP applications and vision transformers. [slides (pdf)] [Link]
Lecture 31 Thursday
Mar 31		 [Link]
Lecture 32 Friday
Apr 01		 [Link]
Guest Lecture Wednesday
Apr 06		 Making Multimodal Learning More Efficient
Speaker: Rameswar Panda, MIT-IBM Watson AI Lab, Cambridge, USA. 		[slides (coming)]
 [Link]
Class test-III on Module 02, 03, 04, 05, 06 (except last lecture) on Apr 07 (Thursday)