EC870 Architectures for Signal Processing and Machine Learning
Course Name:
EC870 Architectures for Signal Processing and Machine Learning
Programme:
Category:
Credits (L-T-P):
Content:
Representation of digital signal processing systems: block diagrams, signal flow graphs, data-flow graphs, dependence graphs; pipelining and parallel processing for high-speed and low power realizations; iteration bound, algorithms to compute iteration bound, retiming of data-flow graphs; unfolding transformation of dataflow graphs; systolic architecture design, architectures for real and complex fast Fourier transforms; stochastic logic based computing, computing digital filters, arithmetic functions and machine learning functions using stochastic computing; Neural Network architectures.