Deep Learning / Jan-May 2023
Updates
- Apr 19: New Lecture is up: (dl-20) Generative Adversarial Networks (GAN) [slides]
- Apr 15: New Lecture is up: (dl-19) Variational Autoencoders [slides]
- Apr 12: New Lecture is up: (dl-18) Autoencoders [slides]
- Apr 10: New Lecture is up: (dl-17) Generative Models [slides]
- Apr 03: New Lecture is up: (dl-16) Self-Attention and Transformers [slides]
- Mar 29: New Lecture is up: (dl-15) Encoder-Decoder Models and Attention [slides]
- Mar 23: New Lecture is up: (dl-14) Word Embeddings [slides]
Course Description
Deep Learning has lately become the driving force behind numerous high-performing AI/ML products deployed in real-world across diverse disciplines. Tech gaints such as Google, Microsoft, Facebook, Amazon, etc. have strongly been employing the Deep Learning workforce in the past few years for developing a wide range of applications in Computer Vision, Natural Processing, etc. Hence, it has become one of the most sough after learning courses in recent times. In this predominantly theory course, we will discuss the various building blocks required to realize the Deep Learning based solutions.
(AI2100/AI5100) Deep Learning Course Contents
Starting from an artificial neuron model, the aim of this course is to understand feed forward and recurrent architectures of Artificial Neural Networks, all the way to the modern Deep Neural Networks. Specifically, we will discuss the basic Neuron models (McCulloch Pitts, Perceptron), Multi-Layer Perceptron (MLP), Convolutional Neural Networks (CNN), and Recurrent Neural Networks (RNN) (LSTM and GRU). We will understand the representational ability of these models along with how to train them using the Gradient Descent technique using the Backpropagation algorithm. Specifically, we will discuss various optimization algorithms such as Nesterov Accelerated Gradient Descent, Adam, AdaGrad and RMSProp, etc. Towards the end, students of this course get exposed to important deep learning frameworks from computer vision and Natural Language Processing such as encoder-decoder architecture, attention mechanism, etc.
Logistics
Class Room: A-LH-1 (02.01.2023 to 15.01.2023 & 18.02.2023 to 02.05.2023), B115 (16.01.2023 to 17.02.2023)
Timings: Slot-B (Monday-10:00-10:55, Wednesday-09:00-09:55, Thursday-11:00-11:55)
Visit this page regularly for the updates and information regarding the course.
