English
Related papers

Related papers: Sigsoftmax: Reanalysis of the Softmax Bottleneck

200 papers

Large language models (LLMs) have numerous real-life applications across various domains, such as natural language translation, sentiment analysis, language modeling, chatbots and conversational agents, creative writing, text…

Machine Learning · Computer Science 2025-02-18 Yeqi Gao , Zhao Song , Junze Yin

Normalization methods improve both optimization and generalization of ConvNets. To further boost performance, the recently-proposed switchable normalization (SN) provides a new perspective for deep learning: it learns to select different…

Computer Vision and Pattern Recognition · Computer Science 2019-03-12 Wenqi Shao , Tianjian Meng , Jingyu Li , Ruimao Zhang , Yudian Li , Xiaogang Wang , Ping Luo

Loss functions steer the optimization direction of recommendation models and are critical to model performance, but have received relatively little attention in recent recommendation research. Among various losses, we find Softmax loss (SL)…

Machine Learning · Computer Science 2023-12-21 Junkang Wu , Jiawei Chen , Jiancan Wu , Wentao Shi , Jizhi Zhang , Xiang Wang

Converting an n-dimensional vector to a probability distribution over n objects is a commonly used component in many machine learning tasks like multiclass classification, multilabel classification, attention mechanisms etc. For this,…

While transformer models exhibit strong in-context learning (ICL) abilities, they often fail to generalize under simple distribution shifts. We analyze these failures and identify Softmax, the scoring function in the attention mechanism, as…

Computation and Language · Computer Science 2026-05-12 Omar Naim , Swarnadeep Bhar , Jérôme Bolte , Nicholas Asher

The loss function used to train a neural network is strongly connected to its output layer from a statistical point of view. This technical report analyzes common activation functions for a neural network output layer, like linear, sigmoid,…

Machine Learning · Computer Science 2025-11-10 Fernando Berzal

To mitigate the problem of having to traverse over the full vocabulary in the softmax normalization of a neural language model, sampling-based training criteria are proposed and investigated in the context of large vocabulary word-based…

Computation and Language · Computer Science 2022-06-20 Zijian Yang , Yingbo Gao , Alexander Gerstenberger , Jintao Jiang , Ralf Schlüter , Hermann Ney

Noisy labels pose a common challenge for training accurate deep neural networks. To mitigate label noise, prior studies have proposed various robust loss functions to achieve noise tolerance in the presence of label noise, particularly…

Machine Learning · Computer Science 2025-08-05 Jialiang Wang , Xiong Zhou , Deming Zhai , Junjun Jiang , Xiangyang Ji , Xianming Liu

This paper questions whether the strong performance of softmax attention in transformers stems from producing a probability distribution over inputs. Instead, we argue that softmax's effectiveness lies in its implicit regularization of the…

Machine Learning · Computer Science 2026-03-16 Hemanth Saratchandran , Jianqiao Zheng , Yiping Ji , Wenbo Zhang , Simon Lucey

Over the past few years, softmax and SGD have become a commonly used component and the default training strategy in CNN frameworks, respectively. However, when optimizing CNNs with SGD, the saturation behavior behind softmax always gives us…

Computer Vision and Pattern Recognition · Computer Science 2017-08-15 Binghui Chen , Weihong Deng , Junping Du

With an eye towards human-centered automation, we contribute to the development of a systematic means to infer features of human decision-making from behavioral data. Motivated by the common use of softmax selection in models of human…

Optimization and Control · Mathematics 2015-09-01 Paul Reverdy , Naomi E. Leonard

With the growing size of large language models, the role of quantization becomes increasingly significant. However, outliers present in weights or activations notably influence the performance of quantized models. Recently,…

Computation and Language · Computer Science 2024-02-20 Baohao Liao , Christof Monz

Mixture-of-experts models provide a flexible framework for learning complex probabilistic input-output relationships by combining multiple expert models through an input-dependent gating mechanism. These models have become increasingly…

Machine Learning · Statistics 2026-04-23 Nicola Bariletto , Huy Nguyen , Nhat Ho , Alessandro Rinaldo

RNN-Transducer has been one of promising architectures for end-to-end automatic speech recognition. Although RNN-Transducer has many advantages including its strong accuracy and streaming-friendly property, its high memory consumption…

Audio and Speech Processing · Electrical Eng. & Systems 2022-04-01 Jaesong Lee , Lukas Lee , Shinji Watanabe

In state-of-the-art deep learning for object recognition, SoftMax and Sigmoid functions are most commonly employed as the predictor outputs. Such layers often produce overconfident predictions rather than proper probabilistic scores, which…

Computer Vision and Pattern Recognition · Computer Science 2022-05-13 Gledson Melotti , Cristiano Premebida , Jordan J. Bird , Diego R. Faria , Nuno Gonçalves

In many scenarios of a language identification task, the user will specify a small set of languages which he/she can speak instead of a large set of all possible languages. We want to model such prior knowledge into the way we train our…

Audio and Speech Processing · Electrical Eng. & Systems 2019-02-19 Li Wan , Prashant Sridhar , Yang Yu , Quan Wang , Ignacio Lopez Moreno

There has long been debates on how we could interpret neural networks and understand the decisions our models make. Specifically, why deep neural networks tend to be error-prone when dealing with samples that output low softmax scores. We…

Computer Vision and Pattern Recognition · Computer Science 2018-12-04 Simiao Zuo , Jialin Wu

Top-K sparse softmax gating mixture of experts has been widely used for scaling up massive deep-learning architectures without increasing the computational cost. Despite its popularity in real-world applications, the theoretical…

Machine Learning · Statistics 2024-02-27 Huy Nguyen , Pedram Akbarian , Fanqi Yan , Nhat Ho

The softmax content-based attention mechanism has proven to be very beneficial in many applications of recurrent neural networks. Nevertheless it suffers from two major computational limitations. First, its computations for an attention…

Machine Learning · Computer Science 2016-09-20 Alexandre de Brébisson , Pascal Vincent

Unsupervised neural grammar induction aims to learn interpretable hierarchical structures from language data. However, existing models face an expressiveness bottleneck, often resulting in unnecessarily large yet underperforming grammars.…

Computation and Language · Computer Science 2025-09-26 Jinwook Park , Kangil Kim
‹ Prev 1 3 4 5 6 7 10 Next ›