Neural Networks

Course description

Neural networks are computational models composed of interconnected nodes that learn to identify complex patterns in data. In this course, students explore the principles of deep learning, including neural network architectures and gradient-based optimization. Neural networks learn by being trained on datasets, either through supervised, unsupervised, or reinforcement learning methods. Students learn how to design, evaluate, and compare neural networks and deploy trained models through simple APIs. Using frameworks such as TensorFlow, PyTorch, or Keras, students develop and optimize neural models using real-world datasets. By the end of the course, students are able to implement and assess neural network solutions for complex AI applications and integrate them into scalable systems

Students registering for credit courses for the first time must declare a program at the point of registration. Declaring a program does not necessarily mean students must complete a program, individual courses may be taken for skill improvement and upgrading.

For more information, please contact Continuing Education