This course provides students with an extensive exposure to deep learning. Topics include shallow and deep neural networks, activation functions and rectified linear unit, construction of deep neural networks and matrix representations including deep convolutional neural networks and Transformer, computational issues including backpropagation, automatic differentiation, and stochastic gradient descent, complexity analysis, approximation analysis including universality of approximation, design of deep neural network architectures and programming according to various applications including computer vision tasks such as detection, segmentation and low-level vision, generative models such as VAE, GAN, Diffusion models and adversarial robustness.

Exam: Administer an exam focused on assessing the comprehension of basic concepts, fundamental theories, various neural network architectures, and their applications to datasets.