Scribd
Upload
67 views

Introduction To Deep Learning: Instructor Email Phone Offic Meeting Hours & Place Office Hours Tas Lecture Notes

This 3 sentence summary provides the key details about the ECSE 4850/6850 Introduction to Deep Learning course at RPI for Spring 2022: The course will be taught by Dr. Qiang Ji on Mondays and Thursdays from 2:00-3:20 pm in Webex/CARNEG 113, and introduces fundamentals of both deterministic and probabilistic deep learning models like neural networks, convolutional neural networks, and generative adversarial networks as applied to computer vision tasks. Students are required to have knowledge of linear algebra, calculus, and programming in C++, Matlab, or Python, and the course will involve homework, projects, a midterm, and final exam evaluated at 15%,

Uploaded by

Ezemaduka Chibuikem
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
67 views

Introduction To Deep Learning: Instructor Email Phone Offic Meeting Hours & Place Office Hours Tas Lecture Notes

This 3 sentence summary provides the key details about the ECSE 4850/6850 Introduction to Deep Learning course at RPI for Spring 2022: The course will be taught by Dr. Qiang Ji on Mondays and Thursdays from 2:00-3:20 pm in Webex/CARNEG 113, and introduces fundamentals of both deterministic and probabilistic deep learning models like neural networks, convolutional neural networks, and generative adversarial networks as applied to computer vision tasks. Students are required to have knowledge of linear algebra, calculus, and programming in C++, Matlab, or Python, and the course will involve homework, projects, a midterm, and final exam evaluated at 15%,

Uploaded by

Ezemaduka Chibuikem
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 1

ECSE 4850/6850

Introduction to Deep Learning


Spring, 2022
Instructor: Dr. Qiang Ji,
Email: [email protected]
Phone: 276-6440
Office: JEC 7004
Meeting Hours & Place : 2:00-3:20 pm, Mondays and Thursdays, Webex/CARNEG 113
Office Hours: 3:30-4:30 pm Thursdays or by Appointment
TAs: Naiyu Yin [email protected]

Lecture notes: Available on RPI Learning Management System


This course introduces fundamentals in deep learning and demonstrates its applications in
computer vision. It covers both deterministic and probabilistic deep models. For deterministic
deep models, the course covers discriminative models, including Deep Neural Networks,
Convolutional Neural Networks, Recurrent Neural Networks, Generative Models (Generative
Adversarial Networks and the auto-encoders), and Deep Reinforcement learning. Probabilistic
deep models include Bayesian Neural Networks, Deep Boltzmann Machine, Deep Belief
Networks, and Deep Bayesian Networks. The course is self-contained. It starts with an
introduction of the background needed for learning deep models, including probability, linear
algebra, standard classification and optimization techniques. To demonstrate various deep
models, we will apply them to different computer vision tasks.

Prerequisites
This is a senior and graduate level course. Students are required to have good
knowledge in linear algebra and multivariate calculus, and basic knowledge in optimization.
Strong programming skills in one of the high level languages such as C++, Matlab, or Python are
required. Prior courses in machine learning/ pattern recognition and computer vision/image
processing are preferred but not required.
Optional textbooks
Deep Learning, Ian Goodfellow and Yoshua Bengio and Aaron Courville, MIT Press,
2016, http://www.deeplearningbook.org (download the book quickly for free!)
Linear Algebra and Learning from Data, Gilbert Strang, Wellesley-Cambridge Press ,
2018.
http://math.mit.edu/~gs/learningfromdata/
Software
Many of the assignments and projects will be implemented in Google’s TensorFlow
(https://www.tensorflow.org/tutorials/), which is implemented in Python. Mastery of Python or
being able to quickly learn it is required.

Course Evaluation
The course will involve homework assignments (15%), class projects (40%), a mid-term
exam (25%), and a final project (20%). All exams are open book and comprehensive.

You might also like