This paper updates the survey of AI accelerators and processors from past three years. This
paper collects and summarizes the current commercial accelerators that have been publicly …

Deep learning has revolutionized many sectors of industry and daily life, but as application
scale increases, performing training and inference with large models on massive datasets is …

Artificial neural networks are very time consuming and energy intensive to train, especially
when increasing the size of the neural network in an attempt to improve the performance. In …

Alternatives to backpropagation have long been studied to better understand how biological
brains may learn. Recently, they have also garnered interest as a way to train neural …

The study of the optical transmission matrix (TM) of a sample reveals important statistics of
light transport through it. The accuracy of the statistics depends strongly on the orthogonality …

This thesis examines the idea that Pavlovian associative learning may be a building block in
neural networks. With emphasis on hardware acceleration, on-chip optical associative …

The topic of this thesis is the development of large-scale optimization algorithms,
popularized by machine learning, for various applications around light propagation through …