M Pfeiffer, T Pfeil - Frontiers in neuroscience, 2018 - frontiersin.org
Spiking neural networks (SNNs) are inspired by information processing in biology, where sparse and asynchronous binary signals are communicated and processed in a massively …
The strength of modern generative models lies in their ability to be controlled through prompts. Hard prompts comprise interpretable words and tokens, and are typically hand …
The binary neural network, largely saving the storage and computation, serves as a promising technique for deploying deep models on resource-limited devices. However, the …
R Gong, X Liu, S Jiang, T Li, P Hu… - Proceedings of the …, 2019 - openaccess.thecvf.com
Hardware-friendly network quantization (eg, binary/uniform quantization) can efficiently accelerate the inference and meanwhile reduce memory consumption of the deep neural …
Communication bottleneck has been identified as a significant issue in distributed optimization of large-scale learning models. Recently, several approaches to mitigate this …
Very deep convolutional neural networks offer excellent recognition results, yet their computational expense limits their impact for many real-world applications. We introduce …
S Wu, G Li, F Chen, L Shi - arXiv preprint arXiv:1802.04680, 2018 - arxiv.org
Researches on deep neural networks with discrete parameters and their deployment in embedded systems have been active and promising topics. Although previous works have …
X Sun, N Wang, CY Chen, J Ni… - Advances in …, 2020 - proceedings.neurips.cc
In this paper, we propose a number of novel techniques and numerical representation formats that enable, for the very first time, the precision of training systems to be aggressively …
Y Guo - arXiv preprint arXiv:1808.04752, 2018 - arxiv.org
Deep neural networks are the state-of-the-art methods for many real-world tasks, such as computer vision, natural language processing and speech recognition. For all its popularity …