Deep Learning and Neural Architectures

3 credits · Undergraduate

Advanced neural network architectures and deep learning techniques. Backpropagation, regularization, transfer learning, and model generalization. Design, implementation, and optimization of deep learning models such as convolutional neural networks (CNNs), recurrent neural networks (RNNs), long short-term memory networks (LSTMs), and Transformers. No credit for students who have earned credit for ECE 5609. Prerequisites: CS 1100, 1101, 1105, or DS 1100; ECE/CS 2123 or ECE/CS 2281 or ME 2171 or BME 2900W or DS 3100 or CE 2200 or CHBE 2250. [3]