English
Related papers

Related papers: Efficient Softmax Approximation for Deep Neural Ne…

200 papers

Deep Neural Networks (DNNs) are computationally and memory intensive, which makes their hardware implementation a challenging task especially for resource constrained devices such as IoT nodes. To address this challenge, this paper…

Computer Vision and Pattern Recognition · Computer Science 2021-05-10 Mohammed F. Tolba , Huruy Tekle Tesfai , Hani Saleh , Baker Mohammad , Mahmoud Al-Qutayri

Softmax is widely used in deep learning to map some representation to a probability distribution. As it is based on exp/log functions that are relatively expensive in multi-party computation, Mohassel and Zhang (2017) proposed a simpler…

Machine Learning · Computer Science 2021-07-07 Marcel Keller , Ke Sun

Transformer-based models have emerged as one of the most widely used architectures for natural language processing, natural language generation, and image generation. The size of the state-of-the-art models has increased steadily reaching…

Hardware Architecture · Computer Science 2025-01-15 Rya Sanovar , Srikant Bharadwaj , Renee St. Amant , Victor Rühle , Saravan Rajmohan

Computations for the softmax function are significantly expensive when the number of output classes is large. In this paper, we present a novel softmax inference speedup method, Doubly Sparse Softmax (DS-Softmax), that leverages sparse…

Machine Learning · Computer Science 2019-07-04 Shun Liao , Ting Chen , Tian Lin , Denny Zhou , Chong Wang

When training early-stage deep neural networks (DNNs), generating intermediate features via convolution or linear layers occupied most of the execution time. Accordingly, extensive research has been done to reduce the computational burden…

Hardware Architecture · Computer Science 2022-11-08 Seock-Hwan Noh , Junsang Park , Dahoon Park , Jahyun Koo , Jeik Choi , Jaeha Kung

As the performance gains from accelerating quantized matrix multiplication plateau, the softmax operation becomes the critical bottleneck in Transformer inference. This bottleneck stems from two hardware limitations: (1) limited data…

Machine Learning · Computer Science 2026-02-03 Zisheng Ye , Xiaoyu He , Maoyuan Song , Guoliang Qiu , Chao Liao , Chen Wu , Yonggang Sun , Zhichun Li , Xiaoru Xie , Yuanyong Luo , Hu Liu , Pinyan Lu , Heng Liao

The transformer's attention mechanism has revolutionized AI and machine learning, with its efficient computation being crucial to its performance. However, calculating attention involves matrix operations interspersed with softmax…

Machine Learning · Computer Science 2025-05-21 Kosmas Alexandridis , Vasileios Titopoulos , Giorgos Dimitrakopoulos

Extensive efforts have been made to boost the performance in the domain of language models by introducing various attention-based transformers. However, the inclusion of linear layers with large dimensions contributes to significant…

Machine Learning · Computer Science 2024-11-19 Priyansh Bhatnagar , Linfeng Wen , Mingu Kang

Transformer networks have emerged as the state-of-the-art approach for natural language processing tasks and are gaining popularity in other domains such as computer vision and audio processing. However, the efficient hardware acceleration…

Hardware Architecture · Computer Science 2024-07-29 Gamze İslamoğlu , Moritz Scherer , Gianna Paulin , Tim Fischer , Victor J. B. Jung , Angelo Garofalo , Luca Benini

The softmax activation function plays a crucial role in the success of large language models (LLMs), particularly in the self-attention mechanism of the widely adopted Transformer architecture. However, the underlying learning dynamics that…

Machine Learning · Computer Science 2026-01-27 Yang Cao , Yingyu Liang , Zhenmei Shi , Zhao Song

Low-bit quantization of network weights and activations can drastically reduce the memory footprint, complexity, energy consumption and latency of Deep Neural Networks (DNNs). However, low-bit quantization can also cause a considerable drop…

Computer Vision and Pattern Recognition · Computer Science 2021-03-25 Ghouthi Boukli Hacene , Lukas Mauch , Stefan Uhlich , Fabien Cardinaux

The use of low numerical precision is a fundamental optimization included in modern accelerators for Deep Neural Networks (DNNs). The number of bits of the numerical representation is set to the minimum precision that is able to retain…

Signal Processing · Electrical Eng. & Systems 2019-11-12 Franyell Silfa , Jose-Maria Arnau , Antonio Gonzàlez

In recent years, the performance of face verification systems has significantly improved using deep convolutional neural networks (DCNNs). A typical pipeline for face verification includes training a deep network for subject classification…

Computer Vision and Pattern Recognition · Computer Science 2017-06-09 Rajeev Ranjan , Carlos D. Castillo , Rama Chellappa

Energy efficiency of hardware accelerators of deep neural networks (DNN) can be improved by introducing approximate arithmetic circuits. In order to quantify the error introduced by using these circuits and avoid the expensive hardware…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-07-03 Filip Vaverka , Vojtech Mrazek , Zdenek Vasicek , Lukas Sekanina

The quadratic computational complexity of softmax transformers has become a bottleneck in long-context scenarios. In contrast, linear attention model families provide a promising direction towards a more efficient sequential model. These…

Computation and Language · Computer Science 2026-02-04 Difan Deng , Andreas Bentzen Winje , Lukas Fehring , Marius Lindauer

The input method is an essential service on every mobile and desktop devices that provides text suggestions. It converts sequential keyboard inputs to the characters in its target language, which is indispensable for Japanese and Chinese…

Computation and Language · Computer Science 2018-10-23 Jiali Yao , Raphael Shu , Xinjian Li , Katsutoshi Ohtsuki , Hideki Nakayama

FPGAs have distinct advantages as a technology for deploying deep neural networks (DNNs) at the edge. Lookup Table (LUT) based networks, where neurons are directly modeled using LUTs, help maximize this promise of offering ultra-low latency…

Machine Learning · Computer Science 2024-09-17 Binglei Lou , Richard Rademacher , David Boland , Philip H. W. Leong

Specialized hardware accelerators have been designed and employed to maximize the performance efficiency of Spiking Neural Networks (SNNs). However, such accelerators are vulnerable to transient faults (i.e., soft errors), which occur due…

Hardware Architecture · Computer Science 2023-03-06 Rachmad Vidya Wicaksana Putra , Muhammad Abdullah Hanif , Muhammad Shafique

Traditional digital implementations of neural accelerators are limited by high power and area overheads, while analog and non-CMOS implementations suffer from noise, device mismatch, and reliability issues. This paper introduces a CMOS…

Transformers have shown remarkable performance in both natural language processing (NLP) and computer vision (CV) tasks. However, their real-time inference speed and efficiency are limited due to the inefficiency in Softmax and Layer…

Machine Learning · Computer Science 2025-10-21 Wenxun Wang , Shuchang Zhou , Wenyu Sun , Peiqin Sun , Yongpan Liu