Robust Networks: Neural Networks Robust to Quantization Noise and Analog Computation Noise Based on Natural Gradient

Robust Networks: Neural Networks Robust to Quantization Noise and Analog Computation Noise Based on Natural Gradient

abstract: Deep neural networks (DNNs) have had tremendous success in a variety of statistical learning applications due to their vast expressive power. Most applications run DNNs on the cloud on parallelized architectures. There is a need for for efficient DNN inference on edge with low precision...

Full description

Bibliographic Details
Other Authors: Kadambi, Pradyumna (Author)
Format: Dissertation
Language:English
Published: 2019
Subjects:
Artificial intelligence
Computer engineering
Computer science
analog neural network
distillation
fisher information
kl-divergence
non-volatile memory accelerator
quantized neural network
Online Access:http://hdl.handle.net/2286/R.I.55679

Internet

http://hdl.handle.net/2286/R.I.55679

Similar Items