The Course Covers Wide Range of Deep Learning Algorithms and Their Efficient Implementation On Dedicated Hardware. in Particular, The Course Will Cover Following Topics# Multilayer Perceptron, Convolutional Networks, Recurrent Networks, Unsupervised Networks, Generative Models, Learning On Graphs, Network Compression Etc. The Hardware Section Will Overview Dedicated Architectures For Training And Accelerating Deep Neural Networks. Learning Outcomes# At The End of The Course, The Student Will# 1. Know The Theoretical and Practical Aspects Constructing Deep Neural Networks. 2. Know How to Construct Deep Neural Networks Using Dedicated Software Frameworks. 3. Know Diverse Optimization Techniques Allowing Efficient Implementation of Machine Learning Applications On Computation Accelerators. 4. Perform a Concluding Research Project.

Faculty: Computer Science
|Undergraduate Studies |Graduate Studies

Pre-required courses

(44198 - Intro. to Digital Signal Processing and 46195 - Machine Learning and 234125 - Numerical Algorithms and 236200 - Signal and 236201 - Introduction to Data Processing And and 236756 - Introduction to Machine Learning)

Semestrial Information