Electrical & Computer Engin 697LS - ST-HardwareDes/MachLrngSyst

Study architectural techniques for efficient hardware design for machine learning (ML) systems including training and inference. Course has three parts. First part deals with ML algorithms: regression, support vector machines, decision tree, and naive Bayes approaches. Second part deals with convolutional and deep neural network models. Last part deals with hardware design involving various acceleration techniques for improving computational efficiency of ML kernels including parallelism, locality, precision in matrix multiplication and convolution; role of batch size, regularization, precision and compression in design space trade-off for efficiency vs accuracy; evaluation of performance, energy efficiency, area, and memory hierarchy. Course will involve Machine Learning Labs in Python using Numpy, Tensorflow and Keras and Verilog for hardware design.

Open to Seniors and Graduate E&C-ENG majors only.