Practicum for Deep Neural Networks

Practicum for Deep Neural Networks

Deep Neural Networks (DNN) have revolutionized the field of artificial intelligence over the past decade, driving significant advancements in "state of the art" AI technologies. Since this course was first introduced in 2018, the field has evolved substantially. In response, the summer 2024 syllabus includes refreshed content and new topics aligned with the latest DNN architectures.

This course provides an introduction to the fundamental concepts of DNN development, covering key architectures and algorithms through a variety of neural network models. Students will engage in detailed analyses of leading deep learning approaches, working with popular networks such as Convolutional Neural Networks (CNN), Fully Connected Neural Networks (FCNN), ImageNet, ResNet, and Recurrent Neural Networks (RNN). Additionally, the course will explore new Generative AI models, with a focus on the "Transformers" architecture foundational to systems like GPT, Copilot, Gemini, and Llama.

Practical exercises using the two most popular AI tools/frameworks will help students develop hands-on skills and confidence in applying machine learning concepts within neural network contexts. By the end of this course, students will have acquired essential deep learning knowledge and skills to create and train neural networks for practical applications.

Learning Outcomes:

• Understand the architecture of deep neural networks (DNN), including different families of DNN models and the taxonomy of DNN architectures.
• Build and train a multilayer perceptron, adapting it to include different layer architectures and comparing performance.
• Apply convolutional neural networks (CNN) in image classification and segmentation tasks.
• Utilize DNNs in natural language processing applications.
• Introduce the concept of Generative AI, focusing on autoregressive model architecture.
• Explore Transformers architecture with a practical walkthrough for building a GPT model for text generation.

The goal of this course is to open career opportunities in the highly sought-after fields of machine learning and AI. The key topics covered will provide insights into how AI can revolutionize your career. Students will also gain a better understanding of the advantages and limitations of Generative AI.

Course typically offered: Online during our Summer and Winter academic quarters.

Prerequisites: CSE-41287: Linear Algebra for Machine Learning and CSE-41305: Probability and Statistics for Deep Learning, or equivilent knowledge.

Next Steps: Upon completion, consider additional coursework in our specialized certificate in Machine Learning Methods to continue learning.

More Information: For more information about this course, please contact unex-techdata@ucsd.edu.

Course Number: CSE-41311
Credit: 3.00 unit(s)
Related Certificate Programs: Machine Learning Methods

+ Expand All

7/9/2024 - 9/7/2024

$775

Online

Closed

• SECTION ID:

  181668

• CLASS TYPE:

  Online Asynchronous.
  
  This course is entirely web-based and to be completed asynchronously between the published course start and end dates. Synchronous attendance is NOT required.
  You will have access to your online course on the published start date OR 1 business day after your enrollment is confirmed if you enroll on or after the published start date.

• INSTRUCTOR:
  

  Aleksic, Bilyana

  Bilyana Aleksic is senior staff hardware engineer with more than 20 years of experience in complex chip SOC development. She received her master's in control systems from Faculty of Electrical Engineering University of Belgrade, former Yugoslavia, and was an honored student of Mathematical Gymnasium, winning many world Mathematical Olympiad Competitions. Aleksic spent 15 years at Canadian tech company ATI Technologies where she worked on implementation of graphics CPU chips. After she moved to California she spent 7 years in mobile chips implementation and verification methodology development. During the past year she shifted her focus to machine learning for medical applications.

• TEXTBOOKS:

  No information available at this time.

• POLICIES:

  No refunds after: 7/15/2024.
  

• NOTE:

• DATE & LOCATION:

  7/9/2024 - 9/7/2024
  extensioncanvas.ucsd.edu
  You will have access to your course materials on the published start date OR 1 business day after your enrollment is confirmed if you enroll on or after the published start date.