English
Related papers

Related papers: Cheetah: Mixed Low-Precision Hardware & Software C…

200 papers

Neural networks have shown great performance in cognitive tasks. When deploying network models on mobile devices with limited resources, weight quantization has been widely adopted. Binary quantization obtains the highest compression but…

Computer Vision and Pattern Recognition · Computer Science 2018-11-14 Hsin-Pai Cheng , Yuanjun Huang , Xuyang Guo , Yifei Huang , Feng Yan , Hai Li , Yiran Chen

As the machine learning and systems communities strive to achieve higher energy-efficiency through custom deep neural network (DNN) accelerators, varied bit precision or quantization levels, there is a need for design space exploration…

Hardware Architecture · Computer Science 2022-05-27 Ahmet Inci , Siri Garudanagiri Virupaksha , Aman Jain , Venkata Vivek Thallam , Ruizhou Ding , Diana Marculescu

The massive computational costs associated with large language model (LLM) pretraining have spurred great interest in reduced-precision floating-point representations to accelerate the process. As a result, the BrainFloat16 (BF16) precision…

Machine Learning · Computer Science 2025-03-26 Joonhyung Lee , Jeongin Bae , Byeongwook Kim , Se Jung Kwon , Dongsoo Lee

When training deep neural networks, keeping all tensors in high precision (e.g., 32-bit or even 16-bit floats) is often wasteful. However, keeping all tensors in low precision (e.g., 8-bit floats) can lead to unacceptable accuracy loss.…

Machine Learning · Computer Science 2023-06-26 Wonyeol Lee , Rahul Sharma , Alex Aiken

Block Floating Point (BFP) can efficiently support quantization for Deep Neural Network (DNN) training by providing a wide dynamic range via a shared exponent across a group of values. In this paper, we propose a Fast First, Accurate Second…

Machine Learning · Computer Science 2021-11-01 Sai Qian Zhang , Bradley McDanel , H. T. Kung

Deep neural networks (DNNs) are becoming increasingly deeper, wider, and non-linear due to the growing demands on prediction accuracy and analysis quality. When training a DNN model, the intermediate activation data must be saved in the…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-11-24 Sian Jin , Guanpeng Li , Shuaiwen Leon Song , Dingwen Tao

Deep neural networks (DNNs) sustain high performance in today's data processing applications. DNN inference is resource-intensive thus is difficult to fit into a mobile device. An alternative is to offload the DNN inference to a cloud…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-01-18 Beibei Zhang , Tian Xiang , Hongxuan Zhang , Te Li , Shiqiang Zhu , Jianjun Gu

Dataset Condensation (DC) distills knowledge from large datasets into smaller ones, accelerating training and reducing storage requirements. However, despite notable progress, prior methods have largely overlooked the potential of…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Linh-Tam Tran , Sung-Ho Bae

The prediction accuracy of the deep neural networks (DNNs) after deployment at the edge can suffer with time due to shifts in the distribution of the new data. To improve robustness of DNNs, they must be able to update themselves to enhance…

Machine Learning · Computer Science 2022-03-23 Kshitij Bhardwaj , James Diffenderfer , Bhavya Kailkhura , Maya Gokhale

Ternary Neural Networks (TNNs) have received much attention due to being potentially orders of magnitude faster in inference, as well as more power efficient, than full-precision counterparts. However, 2 bits are required to encode the…

Machine Learning · Computer Science 2021-07-30 Peng Chen , Bohan Zhuang , Chunhua Shen

In modern low-power embedded platforms, floating-point (FP) operations emerge as a major contributor to the energy consumption of compute-intensive applications with large dynamic range. Experimental evidence shows that 50% of the energy…

Hardware Architecture · Computer Science 2017-11-29 Giuseppe Tagliavini , Stefan Mach , Davide Rossi , Andrea Marongiu , Luca Benini

Deep Neural Networks (DNNs) have shown excellent performance in a wide range of machine learning applications. Knowing the latency of running a DNN model or tensor program on a specific device is useful in various tasks, such as DNN graph-…

Machine Learning · Computer Science 2023-11-20 Hanpeng Hu , Junwei Su , Juntao Zhao , Yanghua Peng , Yibo Zhu , Haibin Lin , Chuan Wu

Deep neural networks have rapidly become the mainstream method for face recognition (FR). However, this limits the deployment of such models that contain an extremely large number of parameters to embedded and low-end devices. In this work,…

Computer Vision and Pattern Recognition · Computer Science 2021-12-14 Fadi Boutros , Patrick Siebke , Marcel Klemt , Naser Damer , Florian Kirchbuchner , Arjan Kuijper

Deep neural networks (DNN) have achieved remarkable success in computer vision (CV). However, training and inference of DNN models are both memory and computation intensive, incurring significant overhead in terms of energy consumption and…

Computer Vision and Pattern Recognition · Computer Science 2021-05-26 Tao Luo , Wai Teng Tang , Matthew Kay Fei Lee , Chuping Qu , Weng-Fai Wong , Rick Goh

We introduce a precision polarization scheme for DNN inference that utilizes only very low and very high precision levels, assigning low precision to the majority of network weights and activations while reserving high precision paths for…

Machine Learning · Computer Science 2024-11-12 Dinithi Jayasuriya , Nastaran Darabi , Maeesha Binte Hashem , Amit Ranjan Trivedi

Training deep neural networks (DNNs) requires significantly more computation and memory than inference, making runtime adaptation of DNNs challenging on resource-limited IoT platforms. We propose InstantFT, an FPGA-based method for…

Machine Learning · Computer Science 2025-06-10 Keisuke Sugiura , Hiroki Matsutani

To improve the throughput and energy efficiency of Deep Neural Networks (DNNs) on customized hardware, lightweight neural networks constrain the weights of DNNs to be a limited combination (denoted as $k\in\{1,2\}$) of powers of 2. In such…

Computer Vision and Pattern Recognition · Computer Science 2019-04-08 Ruizhou Ding , Zeye Liu , Ting-Wu Chin , Diana Marculescu , R. D. , Blanton

In collaborative intelligence applications, part of a deep neural network (DNN) is deployed on a relatively low-complexity device such as a mobile phone or edge device, and the remainder of the DNN is processed where more computing…

Machine Learning · Computer Science 2021-05-14 Robert A. Cohen , Hyomin Choi , Ivan V. Bajić

Federated Learning (FL) preserves privacy by distributing training across devices. However, using DNNs is computationally intensive at the low-powered edge during inference. Edge deployment demands models that simultaneously optimize memory…

Machine Learning · Computer Science 2026-03-17 Nitin Priyadarshini Shankar , Soham Lahiri , Sheetal Kalyani , Saurav Prakash

This work investigates how using reduced precision data in Convolutional Neural Networks (CNNs) affects network accuracy during classification. More specifically, this study considers networks where each layer may use different precision…