Neural Networks and Deep Learning

Graduate

This course introduces the fundamentals of neural networks and deep learning. Neural network architectures are discussed along with their associated set of learning algorithms. Topics include: supervised and unsupervised learning, associative learning, competitive learning, probably approximately correct learning, adaptive learning, gradient-descent and optimization. Students will be required to investigate selected shallow and deep learning models of neural networks, including autoencoders; and convolutional, recurrent, recursive, adversarial and probabilistic networks. Applications of deep learning to computer vision, speech recognition, natural language processing, and others. The legal, societal and ethical implications of artificial intelligence and machine learning are also discussed.