English
Related papers

Related papers: Mixed Precision Training With 8-bit Floating Point

200 papers

While integer arithmetic has been widely adopted for improved performance in deep quantized neural network inference, training remains a task primarily executed using floating point arithmetic. This is because both high dynamic range and…

Computer Vision and Pattern Recognition · Computer Science 2022-02-14 Maolin Wang , Seyedramin Rasoulinezhad , Philip H. W. Leong , Hayden K. H. So

Deep neural networks (DNNs) have been demonstrated as effective prognostic models across various domains, e.g. natural language processing, computer vision, and genomics. However, modern-day DNNs demand high compute and memory storage for…

Distributed, Parallel, and Cluster Computing · Computer Science 2019-03-27 Zachariah Carmichael , Hamed F. Langroudi , Char Khazanov , Jeffrey Lillie , John L. Gustafson , Dhireesha Kudithipudi

We present an overview of techniques for quantizing convolutional neural networks for inference with integer weights and activations. Per-channel quantization of weights and per-layer quantization of activations to 8-bits of precision…

Machine Learning · Computer Science 2018-06-22 Raghuraman Krishnamoorthi

Multi-bit quantization networks enable flexible deployment of deep neural networks by supporting multiple precision levels within a single model. However, existing approaches suffer from significant training overhead as full-dataset updates…

Computer Vision and Pattern Recognition · Computer Science 2025-10-24 Jinhee Kim , Jae Jun An , Kang Eun Jeon , Jong Hwan Ko

Low precision data representation is important to reduce storage size and memory access for convolutional neural networks (CNNs). Yet, existing methods have two major limitations: (1) requiring re-training to maintain accuracy for deep…

Signal Processing · Electrical Eng. & Systems 2020-03-10 Chen Wu , Mingyu Wang , Xinyuan Chu , Kun Wang , Lei He

The resource requirements of deep neural networks (DNNs) pose significant challenges to their deployment on edge devices. Common approaches to address this issue are pruning and mixed-precision quantization, which lead to latency and memory…

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

Deep neural networks (DNNs) have demonstrated remarkable success in various fields. However, the large number of floating-point operations (FLOPs) in DNNs poses challenges for their deployment in resource-constrained applications, e.g.,…

Artificial Intelligence · Computer Science 2024-02-20 Mengnan Jiang , Jingcun Wang , Amro Eldebiky , Xunzhao Yin , Cheng Zhuo , Ing-Chao Lin , Grace Li Zhang

Deep neural networks have achieved state-of-the-art results in a wide range of applications, from natural language processing and computer vision to speech recognition. However, as tasks become increasingly complex, model sizes continue to…

Computer Vision and Pattern Recognition · Computer Science 2025-05-21 Tomer Gafni , Asaf Karnieli , Yair Hanani

Sub-8-bit representation of DNNs incur some discernible loss of accuracy despite rigorous (re)training at low-precision. Such loss of accuracy essentially makes them equivalent to a much shallower counterpart, diminishing the power of being…

Information Theory · Computer Science 2017-11-01 Abhisek Kundu , Kunal Banerjee , Naveen Mellempudi , Dheevatsa Mudigere , Dipankar Das , Bharat Kaul , Pradeep Dubey

We consider the post-training quantization problem, which discretizes the weights of pre-trained deep neural networks without re-training the model. We propose multipoint quantization, a quantization method that approximates a…

Machine Learning · Computer Science 2021-01-15 Xingchao Liu , Mao Ye , Dengyong Zhou , Qiang Liu

Energy and resource efficient training of DNNs will greatly extend the applications of deep learning. However, there are three major obstacles which mandate accurate calculation in high precision. In this paper, we tackle two of them…

Neural and Evolutionary Computing · Computer Science 2018-10-15 Hyunsun Park , Jun Haeng Lee , Youngmin Oh , Sangwon Ha , Seungwon Lee

Reducing hardware overhead of neural networks for faster or lower power inference and training is an active area of research. Uniform quantization using integer multiply-add has been thoroughly investigated, which requires learning many…

Numerical Analysis · Computer Science 2018-11-06 Jeff Johnson

We propose a cluster-based quantization method to convert pre-trained full precision weights into ternary weights with minimal impact on the accuracy. In addition, we also constrain the activations to 8-bits thus enabling sub 8-bit full…

Machine Learning · Computer Science 2017-02-02 Naveen Mellempudi , Abhisek Kundu , Dipankar Das , Dheevatsa Mudigere , Bharat Kaul

Enabling On-Device Learning (ODL) for Ultra-Low-Power Micro-Controller Units (MCUs) is a key step for post-deployment adaptation and fine-tuning of Deep Neural Network (DNN) models in future TinyML applications. This paper tackles this…

Machine Learning · Computer Science 2023-05-31 Davide Nadalini , Manuele Rusci , Luca Benini , Francesco Conti

Large models training is plagued by the intense compute cost and limited hardware memory. A practical solution is low-precision representation but is troubled by loss in numerical accuracy and unstable training rendering the model less…

Deep neural network (DNN) quantization converting floating-point (FP) data in the network to integers (INT) is an effective way to shrink the model size for memory saving and simplify the operations for compute acceleration. Recently,…

Machine Learning · Computer Science 2020-01-01 Yukuan Yang , Shuang Wu , Lei Deng , Tianyi Yan , Yuan Xie , Guoqi Li

The large computing and memory cost of deep neural networks (DNNs) often precludes their use in resource-constrained devices. Quantizing the parameters and operations to lower bit-precision offers substantial memory and energy savings for…

Machine Learning · Computer Science 2023-09-01 Clemens JS Schaefer , Siddharth Joshi , Shan Li , Raul Blazquez

With ever-increasing computational demand for deep learning, it is critical to investigate the implications of the numeric representation and precision of DNN model weights and activations on computational efficiency. In this work, we…

Deep neural networks (DNNs) have enabled smart applications on hardware devices. However, these hardware devices are vulnerable to unintended faults caused by aging, temperature variance, and write errors. These faults can cause bit-flips…

Machine Learning · Computer Science 2024-12-02 Ninnart Fuengfusin , Hakaru Tamukoh