Course:
Course Program:
Catalog Description:
Convolutional neural networks. Autoencoders, their sparse, denoising variants, and their training. Regularization methods for preventing overfitting. Stacked autoencoders and end-to-end networks. Recurrent and recursive networks. Multimodal approaches. Deep architectures for vision, speech, natural language processing, and reinforcement learning.
Prerequisite: This is an advanced course on machine learning so you should have a good knowledge of the essential machine learning algorithms (Cmpe 544 and 545).
Textbook:
I Goodfellow, Y Bengio, A Courville (2016). Deep Learning, The MIT Press (see www.deeplearningbook.org), and additional articles when necessary.
Grading:
%30 In-class presentation
%40 Project
%30 Final exam