English
Related papers

Related papers: Reduced Softmax Unit for Deep Neural Network Accel…

200 papers

Deep neural networks (DNN) have demonstrated effectiveness for various applications such as image processing, video segmentation, and speech recognition. Running state-of-the-art DNNs on current systems mostly relies on either…

Neural and Evolutionary Computing · Computer Science 2019-04-15 Mohsen Imani , Mohammad Samragh , Yeseong Kim , Saransh Gupta , Farinaz Koushanfar , Tajana Rosing

The performance of artificial neural networks (ANNs) is influenced by weight initialization, the nature of activation functions, and their architecture. There is a wide range of activation functions that are traditionally used to train a…

Machine Learning · Statistics 2018-11-30 Saeid Safaei , Vahid Safaei , Solmazi Safaei , Zerotti Woods , Hamid R. Arabnia , Juan B. Gutierrez

We introduce LL-RNNs (Log-Linear RNNs), an extension of Recurrent Neural Networks that replaces the softmax output layer by a log-linear output layer, of which the softmax is a special case. This conceptually simple move has two main…

Artificial Intelligence · Computer Science 2016-12-19 Marc Dymetman , Chunyang Xiao

Deep neural networks (DNNs) for supervised learning can be viewed as a pipeline of a feature extractor (i.e. last hidden layer) and a linear classifier (i.e. output layer) that is trained jointly with stochastic gradient descent (SGD). In…

Machine Learning · Computer Science 2020-02-28 Xiangrui Li , Deng Pan , Xin Li , Dongxiao Zhu

In large-scale domain classification for natural language understanding, leveraging each user's domain enablement information, which refers to the preferred or authenticated domains by the user, with attention mechanism has been shown to…

Computation and Language · Computer Science 2018-12-19 Joo-Kyung Kim , Young-Bum Kim

A pivotal aspect in the design of neural networks lies in selecting activation functions, crucial for introducing nonlinear structures that capture intricate input-output patterns. While the effectiveness of adaptive or trainable activation…

Machine Learning · Computer Science 2024-08-06 Farhad Pourkamali-Anaraki , Tahamina Nasrin , Robert E. Jensen , Amy M. Peterson , Christopher J. Hansen

We propose a kernelized classification layer for deep networks. Although conventional deep networks introduce an abundance of nonlinearity for representation (feature) learning, they almost universally use a linear classifier on the learned…

Machine Learning · Computer Science 2021-03-22 Sadeep Jayasumana , Srikumar Ramalingam , Sanjiv Kumar

Maximizing the separation between classes constitutes a well-known inductive bias in machine learning and a pillar of many traditional algorithms. By default, deep networks are not equipped with this inductive bias and therefore many…

Machine Learning · Computer Science 2022-10-25 Tejaswi Kasarla , Gertjan J. Burghouts , Max van Spengler , Elise van der Pol , Rita Cucchiara , Pascal Mettes

The primary neural networks decision-making units are activation functions. Moreover, they evaluate the output of networks neural node; thus, they are essential for the performance of the whole network. Hence, it is critical to choose the…

Machine Learning · Computer Science 2020-10-20 Tomasz Szandała

Complex Deep Neural Networks such as Capsule Networks (CapsNets) exhibit high learning capabilities at the cost of compute-intensive operations. To enable their deployment on edge devices, we propose to leverage approximate computing for…

Machine Learning · Computer Science 2022-06-22 Alberto Marchisio , Beatrice Bussolino , Edoardo Salvati , Maurizio Martina , Guido Masera , Muhammad Shafique

Deep neural networks can suffer from the exploding and vanishing activation problem, in which the networks fail to train properly because the neural signals either amplify or attenuate across the layers and become saturated. While other…

Machine Learning · Computer Science 2021-08-24 Hao-Yuan Chang , Kang L. Wang

This paper presents a framework in which hierarchical softmax is used to create a global hierarchical classifier. The approach is applicable for any classification task where there is a natural hierarchy among classes. We show empirical…

Machine Learning · Statistics 2023-08-03 Jetze Schuurmans , Flavius Frasincar

We investigate the computational complexity of various problems for simple recurrent neural networks (RNNs) as formal models for recognizing weighted languages. We focus on the single-layer, ReLU-activation, rational-weight RNNs with…

Formal Languages and Automata Theory · Computer Science 2018-03-06 Yining Chen , Sorcha Gilroy , Andreas Maletti , Jonathan May , Kevin Knight

In recent years, neural networks have enjoyed a renaissance as function approximators in reinforcement learning. Two decades after Tesauro's TD-Gammon achieved near top-level human performance in backgammon, the deep reinforcement learning…

Machine Learning · Computer Science 2017-11-03 Stefan Elfwing , Eiji Uchibe , Kenji Doya

Deep Neural Networks, and specifically fully-connected convolutional neural networks are achieving remarkable results across a wide variety of domains. They have been trained to achieve state-of-the-art performance when applied to problems…

Information Retrieval · Computer Science 2017-02-07 Zeeshan Khawar Malik , Mo Kobrosli , Peter Maas

Cross-entropy loss together with softmax is arguably one of the most common used supervision components in convolutional neural networks (CNNs). Despite its simplicity, popularity and excellent performance, the component does not explicitly…

Machine Learning · Statistics 2017-11-21 Weiyang Liu , Yandong Wen , Zhiding Yu , Meng Yang

In recent years, the softmax model and its fast approximations have become the de-facto loss functions for deep neural networks when dealing with multi-class prediction. This loss has been extended to language modeling and recommendation,…

Machine Learning · Statistics 2019-09-19 Ugo Tanielian , Flavian Vasile

The majority of the research on the quantization of Deep Neural Networks (DNNs) is focused on reducing the precision of tensors visible by high-level frameworks (e.g., weights, activations, and gradients). However, current hardware still…

Machine Learning · Computer Science 2024-01-26 Yaniv Blumenfeld , Itay Hubara , Daniel Soudry

The softmax function is a fundamental component in deep learning. This study delves into the often-overlooked parameter within the softmax function, known as "temperature," providing novel insights into the practical and theoretical aspects…

Machine Learning · Computer Science 2025-03-03 Hao Xuan , Bokai Yang , Xingyu Li

The attention mechanism is a pivotal element within the transformer architecture, making a substantial contribution to its exceptional performance. Within this attention mechanism, Softmax is an imperative component that enables the model…

Hardware Architecture · Computer Science 2024-09-05 Tianhua Xia , Sai Qian Zhang