OMSCS Seminar: Deep Learning and Generative AI Essentials

  • Overview
  • Course Content
  • Requirements & Materials
Overview

OMSCS Seminar: Deep Learning and Generative AI Essentials

Course Description

Deep learning forms the foundation of modern artificial intelligence systems, enabling computers to learn complex patterns from large datasets and perform tasks such as image recognition, language understanding, and decision-making. Participants will explore the building blocks of neural networks and gain exposure to key generative AI techniques, including Autoencoders, Generative Adversarial Networks (GANs), and Diffusion Models. The seminar also includes optional, ungraded, instructor-led synchronous workshops, sponsored by NVIDIA DLI. These workshops offer cloud GPU access for deeper hands-on practice and provide opportunities to earn NVIDIA certificates of competency upon successful completion of each workshop in the series.

Course Content

This seminar is organized as a series of modules, each consisting of lectures, notebooks, write-ups, and discussions. Designed for learners from all backgrounds, it offers an intuitive, hands-on introduction to the foundational concepts of deep learning and generative AI, emphasizing practical understanding over heavy mathematical theory.

  • Module 4.1 Workshops Overview: Access four NVIDIA-sponsored workshops. While entirely optional, they provide valuable hands-on experience with cutting-edge agentic AI development tools and concepts.
  • Module 4.1.1 Fundamentals of Deep Learning (FDL):Learn the fundamental techniques and tools required to train deep learning models using PyTorch. Topics include CNNs, transfer learning, data augmentation, and NLP fundamentals.
  • Module 4.1.2 AI for Anomaly Detection (ANOM): Detect anomalies in both labeled and unlabeled data using GPU-accelerated XGBoost, autoencoders, and GANs. Apply anomaly detection in cybersecurity, finance, manufacturing, and more.
  • Module 4.1.3 Generative AI with Diffusion Models (DIFF): Build denoising diffusion models using U-Nets, control outputs with context embeddings, and generate text-to-image results using CLIP.
  • Module 4.1.4 Data Parallelism with Multiple GPUs (DPAR): Learn to distribute data and train deep learning models across multiple GPUs with PyTorch DDP and NCCL. Topics include performance scaling, parallelism, and training efficiency.
Requirements & Materials

Prerequisites

RECOMMENDED:

Jupyter Notebook: Recommended but not mandatory
 
REQUIRED:

Python: beginner level

Materials

PROVIDED (Student will receive):

All content is available in Canvas.

Session Details

Who Should Attend

This seminar is designed for OMSCS students and alumni who want to understand the foundations of deep learning and generative AI in a hands-on, approachable way. Attendees may include OMSCS students, career switchers, and professionals from creative, technical, or scientific fields curious about how generative models work and how they can be applied in their respective industries.

Computer science students coding on computers

What You Will Learn

  • An introduction to the foundational building blocks of deep learning and train neural networks using PyTorch
  • AI to detect anomalies in complex datasets using techniques like XGBoost, autoencoders, and GANs
  • Acceleration of deep learning workflows by distributing training across multiple GPUs with PyTorch Distributed Data Parallel
Female professional in computer science lab looking at tablet

How You Will Benefit

  • Understand how to design and train denoising diffusion models for generative tasks using CLIP and U-Nets.
  • Become familiar with generative AI and deep learning.
  • Reflect critically on the applicability and limitations of deep learning and generative AI in real-world domains through peer discussions and structured write-ups.
  • Grow Your Professional Network icon
    Grow Your Professional Network
  • Taught by Experts in the Field icon
    Taught by Experts in the Field

TRAIN AT YOUR LOCATION

We enable employers to provide specialized, on-location training on their own timetables. Our world-renowned experts can create unique content that meets your employees' specific needs. We also have the ability to deliver courses via web conferencing or on-demand online videos. For 15 or more students, it is more cost-effective for us to come to you.

  • Save Money
  • Flexible Schedule
  • Group Training
  • Customize Content
  • On-Site Training
  • Earn a Certificate
Learn More

Want to learn more about this course?