Academics / Courses / DescriptionsELEC_ENG 335, 435: Deep Learning Foundations from Scratch
VIEW ALL COURSE TIMES AND SESSIONS
Prerequisites
Prior machine learning experience (e.g., an introductory machine learning course ELEC_ENG 375/475 or COMP_SCI 349 or a similar course), a thorough understanding of Linear Algebra and Vector Calculus, and strong familiarity with the Python programming language (e.g., basic data manipulation libraries, how to construct functions and classes, etc.). Python will be used for all coding assignments. No other language can be used to complete programming assignments.Description
The last decade has seen a resurgence of deep neural networks as the machine learning tool of choice for many application areas including computer vision, reinforcement learning, and natural language processing. This course offers a holistic and hands-on introduction to deep networks, their many varieties and applications, as well as the algorithms used to train them. In this course we discuss the foundations of Feedforward Networks, Convolutional Networks, and Recurrent Networks, as well as their usage within popular Reinforcement Learning frameworks. Using real datasets and basic Python libraries for data manipulation, vector/matrix algebra, and automatic differentiation students will code up - from scratch - popular examples of each such network architecture and apply them to applications in natural language processing, computer vision, speech recognition, and automatic control.
- This course fulfills the Technical Elective requirement.
INSTRUCTOR: Prof. Aggelos Katsaggelos
COURSE OUTLINE:
1. Deep Feedforward Networks
- a. Supervised learning recap
- b. Feedforward networks in the context of function approximation
- c. Simple recipes for building deep networks
- d. Deep nets vs Kernel methods
- e. How deep networks came back
2. Technical Issues with Deep Networks
- a. Mathematical optimization recap
- b. Automatic differentiation, implementations in Python
- c. First order stochastic gradient methods
- d. Regularization techniques
- e. Technical tricks
3. Convolutional Networks
- a. From fixed feature extractors to convolutional networks
- b. Composing filters and functions
- c. Applications in computer vision and speech processing
- d. Transfer Learning
4. Recurrent Networks
- a. Recurrence relations
- b. Parameterized recurrence relations and feedforward networks
- c. Deriving vanilla recurrent networks
- d. Popular architectures, Long-Short-Term-Memory
- e. Applications in NLP and speech recognition
5. Deep Representation Learning
- a. Unsupervised learning recap
- b. Nonlinear extensions of PCA, autoencoders
COURSE HAND-OUTS: This course has no required textbook. Handouts authored by the instructors will be made freely available to students for notes. In addition a small number of relevant sections from the author’s textbook Machine Learning Refined (Cambridge University Press) will be made freely available to students.
PROBLEM SETS: 4-5 problem sets will be assigned and graded.
COURSE PROJECT: There will be a project for the course
COURSE GRADE: Final grades for the course are based on homework (65%) and project (35%)