Practicum for Deep Neural Networks

Hands-on Training in Building and Deploying Modern Deep Learning Models Deep Neural Networks (DNNs) have transformed artificial intelligence through breakthroughs in image recognition, speech processing, and natural language understanding.

These advances power today’s most innovative AI applications and Generative AI systems.

In this course, you will gain practical experience in deep neural network development, exploring key architectures and algorithms used in modern machine learning.

The course covers popular models such as fully connected neural networks (FCNN), convolutional neural networks (CNN), recurrent neural networks (RNN), and Transformers.

Using the TensorFlow framework, you will build, train, and evaluate neural network models for real-world problems in computer vision and natural language processing.

By the end of the course, you will understand both the strengths and limitations of deep learning and Generative AI, and be prepared to apply these technologies in professional and research environments.

Course Highlights Fundamentals and taxonomy of deep neural network (DNN) architectures Multilayer perceptrons (MLP) and performance comparison of layer designs Convolutional neural networks (CNN) for image classification and segmentation Recurrent neural networks (RNN) for sequence and text processing Introduction to Generative AI and autoregressive models Transformers architecture and GPT-style text generation models Hands-on deep learning projects using TensorFlow Course Benefits Gain practical skills in building and training deep neural networks Understand key AI architectures used in computer vision and NLP Learn how Generative AI models work and where they can be applied Apply deep learning techniques to real-world problems Prepare for careers in machine learning and artificial intelligence Credit earned may be applied toward an academic degree or professional credential, subject to the approval of the receiving institution(s) Course Details and Next Steps Course typically offered: Online in Summer and Winter quarters Prerequisites: CSE-41287: Linear Algebra for Machine Learning and CSE-41305: Probability and Statistics for Deep Learning or equivalent 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