“Deep Learning” systems, typified by deep neural networks, are

increasingly becoming an essential element for most AI tasks, ranging

from language understanding, and speech and image recognition, to

machine translation, planning, game playing, and autonomous

driving. As a result, expertise in deep learning has become a

mandatory prerequisite in many advanced academic settings, and a large

advantage in the industrial job market.

In this course we will learn about the basics of deep neural networks,

and their applications to various AI tasks. By the end of the course,

it is expected that students will have good familiarity with the

subject, and be able to apply Deep Learning to a variety of

tasks. They will also be positioned to understand the current

literature on the topic and extend their knowledge through further

study.

The course is well rounded in terms of concepts. It helps us

understand the fundamentals of Deep Learning. The course starts off

gradually with MLPs and it progresses into the more complicated

concepts such as attention and sequence-to-sequence models. We will

utilize PyTorch which is important to implement Deep Learning

models. As a student, you will learn the tools required for building

Deep Learning models. The homeworks will also involve Kaggle. The

Kaggle components allow us to explore multiple architectures and

understand how to fine-tune and improve models. The task for all the

homeworks were similar and it was interesting to learn how the same

task can be solved using multiple Deep Learning approaches. Overall,

at the end of this course you will be confident enough to build and

tune Deep Learning models.

Class is adapted from from CMU 11785.