Course Description
Students will learn the foundations of Deep Learning, understand how to build neural networks, and learn how to lead and implement successful Deep Learning projects. Students will learn about convolutional networks, recurrent neural networks, and long short-term memory. The basics of machine learning will also be covered.
Additional Requirements for Graduate Students:
Graduate students are required to propose their own deep learning engineering project based on a literature survey of selected course topics. They are expected to design and develop their own code, share it for assessment, present their work, and submit a final project report.
Athena Title
Deep Learning
Undergraduate Prerequisite
ECSE 4410/6410
Graduate Prerequisite
ECSE 4410/6410 and permission of department
Semester Course Offered
Offered every year.
Grading System
A - F (Traditional)
Course Objectives
Student learning outcomes are designed to specify what both undergraduate and graduate students will be able to perform after completion of the course: o Ability to select and implement DL techniques in a computing environment, which is suitable for engineering applications o Ability to prototype, model, and test various DL algorithms o Ability to identify the characteristics of datasets, pre-process them, and compare the impact of using different datasets on DL system performance o Ability to integrate DL libraries and mathematical and statistical tools with modern technologies (MATLAB, Python) o Ability to understand different types of metrics available to evaluate the performance of DL engineering solutions o Ability to select a prototyped model and make it work on a practical scenario, first at small and then at a larger scale Additional course objectives or expected learning outcomes for Graduate Students: o Ability to solve problems associated with batch learning and large-scale data characteristics, including high dimensionality, dynamically growing data, and scalability issues o Ability to understand and apply scaling up DL approaches and associated computing techniques and technologies (e.g., data augmentation) o Ability to recognize and implement various ways of selecting suitable model parameters for different DL techniques o Graduate students will also perform a relevant literature study and project related to the course topics listed
Topical Outline
This course will introduce a graduate audience to salient topics in Deep Learning: • Linear Algebra • Probability and Information Theory • Machine Learning Basics • Deep Feedforward Networks • Regularization for Deep Learning • Optimization for Training Deep Models • Gradient Descent and Structure of Neural Network Cost Functions • Convolutional Networks • Practical Methodology • Autoencoders • Representation Learning The topics will be taught not necessarily in the above order. The project component of this course will test the student's ability to design and evaluate classifiers on appropriate datasets.
Syllabus