English
Related papers

Related papers: Softermax: Hardware/Software Co-Design of an Effic…

200 papers

This paper proposes a novel procedure for training an encoder-decoder based deep neural network which compresses NxM models into a single model enabling us to dynamically choose the number of encoder and decoder layers for decoding.…

Computation and Language · Computer Science 2019-08-29 Raj Dabre , Atsushi Fujita

Spike-based transformer is a novel architecture aiming to enhance the performance of spiking neural networks while mitigating the energy overhead inherent to transformers. However, methods for generating these models suffer from critical…

Computer Vision and Pattern Recognition · Computer Science 2025-09-23 Yuhao Zhang , Chengjun Zhang , Di Wu , Jie Yang , Mohamad Sawan

Typically, Softmax is used in the final layer of a neural network to get a probability distribution for output classes. But the main problem with Softmax is that it is computationally expensive for large scale data sets with large number of…

Machine Learning · Computer Science 2018-12-17 Abdul Arfat Mohammed , Venkatesh Umaashankar

Recent advances in language modeling consist in pretraining highly parameterized neural networks on extremely large web-mined text corpora. Training and inference with such models can be costly in practice, which incentivizes the use of…

Computation and Language · Computer Science 2024-04-12 Nathan Godey , Éric de la Clergerie , Benoît Sagot

The softmax function is a fundamental building block of deep neural networks, commonly used to define output distributions in classification tasks or attention weights in transformer architectures. Despite its widespread use and proven…

Machine Learning · Computer Science 2025-06-03 Wojciech Masarczyk , Mateusz Ostaszewski , Tin Sum Cheng , Tomasz Trzciński , Aurelien Lucchi , Razvan Pascanu

In this work, we show that saturating output activation functions, such as the softmax, impede learning on a number of standard classification tasks. Moreover, we present results showing that the utility of softmax does not stem from the…

Machine Learning · Computer Science 2017-07-14 Anders Oland , Aayush Bansal , Roger B. Dannenberg , Bhiksha Raj

Transformer architecture has become ubiquitous in the natural language processing field. To interpret the Transformer-based models, their attention patterns have been extensively analyzed. However, the Transformer architecture is not only…

Computation and Language · Computer Science 2021-09-16 Goro Kobayashi , Tatsuki Kuribayashi , Sho Yokoi , Kentaro Inui

This work introduces novel training and post-training compression schemes to reduce external memory access during transformer model inference. Additionally, a new control flow mechanism, called dynamic batching, and a novel buffer…

Hardware Architecture · Computer Science 2025-03-04 Seunghyun Moon , Mao Li , Gregory Chen , Phil Knag , Ram Krishnamurthy , Mingoo Seok

Multilayer transformer networks consist of interleaved self-attention and feedforward sublayers. Could ordering the sublayers in a different pattern lead to better performance? We generate randomly ordered transformers and train them with…

Computation and Language · Computer Science 2020-04-24 Ofir Press , Noah A. Smith , Omer Levy

While the approximation properties of single-layer Transformer architectures have been studied in recent works, a rigorous theoretical understanding of the multi-layer setting remains limited. In this work, we establish that multi-layer…

Machine Learning · Computer Science 2026-05-19 Penghao Yu , Haotian Jiang , Zeyu Bao , Qianxiao Li

This is a work-in-progress report, which aims to share preliminary results of a novel sequence-to-sequence schema for dependency parsing that relies on a combination of a BiLSTM and two Pointer Networks (Vinyals et al., 2015), in which the…

Computation and Language · Computer Science 2019-03-19 Matteo Grella

Transformer architecture has become the de-facto model for many machine learning tasks from natural language processing and computer vision. As such, improving its computational efficiency becomes paramount. One of the major computational…

Computation and Language · Computer Science 2022-05-17 Yue Guan , Zhengyi Li , Jingwen Leng , Zhouhan Lin , Minyi Guo

Transformers have recently revolutionized many domains in modern machine learning and one salient discovery is their remarkable in-context learning capability, where models can solve an unseen task by utilizing task-specific prompts without…

Machine Learning · Computer Science 2023-10-10 Yu Huang , Yuan Cheng , Yingbin Liang

Softmax is a standard final layer used in Neural Nets (NNs) to summarize information encoded in the trained NN and return a prediction. However, Softmax leverages only a subset of the class-specific structure encoded in the trained model…

Machine Learning · Computer Science 2019-12-09 Charles B. Delahunt , Courosh Mehanian , J. Nathan Kutz

As an emerging type of Neural Networks (NNs), Transformers are used in many domains ranging from Natural Language Processing to Autonomous Driving. In this paper, we study the robustness problem of Transformers, a key characteristic as low…

Machine Learning · Computer Science 2024-12-03 Brian Hsuan-Cheng Liao , Chih-Hong Cheng , Hasan Esen , Alois Knoll

Transformers have demonstrated great power in the recent development of large foundational models. In particular, the Vision Transformer (ViT) has brought revolutionary changes to the field of vision, achieving significant accomplishments…

Machine Learning · Computer Science 2024-11-25 Jiarui Jiang , Wei Huang , Miao Zhang , Taiji Suzuki , Liqiang Nie

The computational cost of softmax-based attention in transformers limits their applicability to long-context tasks. Adaptive sparsity, of which $\alpha$-entmax attention is an example, offers a flexible data-dependent alternative, but…

Computation and Language · Computer Science 2025-06-10 Nuno Gonçalves , Marcos Treviso , André F. T. Martins

Transformers have greatly advanced the state-of-the-art in Natural Language Processing (NLP) in recent years, but present very large computation and storage requirements. We observe that the design process of Transformers (pre-train a…

Computation and Language · Computer Science 2022-06-13 Amrit Nagarajan , Sanchari Sen , Jacob R. Stevens , Anand Raghunathan

Transformer-based neural networks have achieved state-of-the-art task performance in a number of machine learning domains including natural language processing and computer vision. To further improve their accuracy, recent work has explored…

Machine Learning · Computer Science 2022-09-01 Salar Latifi , Saurav Muralidharan , Michael Garland

Softmax is widely used in neural networks for multiclass classification, gate structure and attention mechanisms. The statistical assumption that the input is normal distributed supports the gradient stability of Softmax. However, when used…

Computer Vision and Pattern Recognition · Computer Science 2021-08-17 Shulun Wang , Bin Liu , Feng Liu