64 citations · 87 across the 5 of their papers we have counts for
4 papers
Training Bit Fully Convolutional Network for Fast Semantic Segmentation
He Wen, Shuchang Zhou, Zhe Liang +4
Fully convolutional neural networks give accurate, per-pixel prediction for input images and have applications like semantic segmentation. However, a typical FCN usually requires l…
Effective Quantization Methods for Recurrent Neural Networks
Qinyao He, He Wen, Shuchang Zhou +4
Reducing bit-widths of weights, activations, and gradients of a Neural Network can shrink its storage size and memory usage, and also allow for faster training and inference by exp…
Critical Remarks on Landauer's principle of erasure-dissipation
Laszlo B. Kish, Claes-Goran Granqvist, Sunil P. Khatri +1
We briefly address Landauer's Principle and some related issues in thermal demons. We show that an error-free Turing computer works in the zero-entropy limit, which proves Landauer…
High-dimensional noise-based logical controller
H. Wen, L. B. Kish, G. Schmera
We introduce a scheme for controlling physical and other quantities; utilizing noise-based logic for control-and-optimization with high dimensionality, similarly how the Hilbert sp…