English
Related papers

Related papers: Breaking the Activation Function Bottleneck throug…

200 papers

Nonlinear interactions in the dendritic tree play a key role in neural computation. Nevertheless, modeling frameworks aimed at the construction of large-scale, functional spiking neural networks, such as the Neural Engineering Framework,…

Neurons and Cognition · Quantitative Biology 2021-01-01 Andreas Stöckel , Chris Eliasmith

The performance of Neural Network (NN)-based language models is steadily improving due to the emergence of new architectures, which are able to learn different natural language characteristics. This paper presents a novel framework, which…

Computation and Language · Computer Science 2017-08-24 Youssef Oualil , Dietrich Klakow

Low-resource languages (LRLs) face significant challenges in natural language processing (NLP) due to limited data. While current state-of-the-art large language models (LLMs) still struggle with LRLs, smaller multilingual models (mLMs)…

Computation and Language · Computer Science 2025-02-17 Daniil Gurgurov , Ivan Vykopal , Josef van Genabith , Simon Ostermann

We propose a new architectural change, and post-training pipeline, for making LLMs more verbose reasoners by teaching a model to truncate forward passes early. We augment an existing transformer architecture with an early-exit mechanism at…

Artificial Intelligence · Computer Science 2026-03-25 Elizabeth Pavlova , Mariia Koroliuk , Karthik Viswanathan , Cameron Tice , Edward James Young , Puria Radmard

Gradient-based neural network training traditionally enforces symmetry between forward and backward propagation, requiring activation functions to be differentiable (or sub-differentiable) and strictly monotonic in certain regions to…

Neural and Evolutionary Computing · Computer Science 2025-09-10 Luigi Troiano , Francesco Gissi , Vincenzo Benedetto , Genny Tortora

To improve how neural networks function it is crucial to understand their learning process. The information bottleneck theory of deep learning proposes that neural networks achieve good generalization by compressing their representations to…

Machine Learning · Computer Science 2023-04-03 Ivan Chelombiev , Conor Houghton , Cian O'Donnell

We propose a general framework to extract microscopic interactions from raw configurations with deep neural networks. The approach replaces the modeling Hamiltonian by the neural networks, in which the interaction is encoded. It can be…

Computational Physics · Physics 2020-08-19 Lingxiao Wang , Yin Jiang , Kai Zhou

Advancements in foundation models (FMs) have led to a paradigm shift in machine learning. The rich, expressive feature representations from these pre-trained, large-scale FMs are leveraged for multiple downstream tasks, usually via…

Machine Learning · Computer Science 2024-12-19 Jihye Choi , Jayaram Raghuram , Yixuan Li , Somesh Jha

We propose a neural language model capable of unsupervised syntactic structure induction. The model leverages the structure information to form better semantic representations and better language modeling. Standard recurrent neural networks…

Computation and Language · Computer Science 2018-02-20 Yikang Shen , Zhouhan Lin , Chin-Wei Huang , Aaron Courville

Modeling the parser state is key to good performance in transition-based parsing. Recurrent Neural Networks considerably improved the performance of transition-based systems by modelling the global state, e.g. stack-LSTM parsers, or local…

Computation and Language · Computer Science 2020-10-22 Ramon Fernandez Astudillo , Miguel Ballesteros , Tahira Naseem , Austin Blodgett , Radu Florian

Pre-trained language models (PTLMs) acquire domain-independent linguistic knowledge through pre-training with massive textual resources. Additional pre-training is effective in adapting PTLMs to domains that are not well covered by the…

Computation and Language · Computer Science 2021-09-20 Kosuke Nishida , Kyosuke Nishida , Sen Yoshida

Recurrent neural networks (RNNs) serve as a fundamental building block for many sequence tasks across natural language processing. Recent research has focused on recurrent dropout techniques or custom RNN cells in order to improve…

Computation and Language · Computer Science 2017-08-04 Stephen Merity , Bryan McCann , Richard Socher

Multitask learning algorithms are typically designed assuming some fixed, a priori known latent structure shared by all the tasks. However, it is usually unclear what type of latent task structure is the most appropriate for a given…

Machine Learning · Computer Science 2012-07-03 Alexandre Passos , Piyush Rai , Jacques Wainer , Hal Daume

Neural networks can be compressed to reduce memory and computational requirements, or to increase accuracy by facilitating the use of a larger base architecture. In this paper we focus on pruning individual neurons, which can simultaneously…

Computer Vision and Pattern Recognition · Computer Science 2018-04-20 Bin Dai , Chen Zhu , David Wipf

Linearization has emerged as a strategy for developing efficient language models (LMs). Starting from an existing Transformer-based LM, linearization replaces the attention component with computationally efficient subquadratic \textit{token…

Computation and Language · Computer Science 2026-02-02 Patrick Haller , Jonas Golde , Alan Akbik

Transfer learning with large pretrained transformer-based language models like BERT has become a dominating approach for most NLP tasks. Simply fine-tuning those large language models on downstream tasks or combining it with task-specific…

Computation and Language · Computer Science 2021-08-06 Wenjuan Han , Bo Pang , Yingnian Wu

Neural networks are traditionally trained under the assumption that data come from a stationary distribution. However, settings which violate this assumption are becoming more popular; examples include supervised learning under…

Machine Learning · Computer Science 2024-11-11 Alexandre Galashov , Michalis K. Titsias , András György , Clare Lyle , Razvan Pascanu , Yee Whye Teh , Maneesh Sahani

Neural networks trained with backpropagation often struggle to identify classes that have been observed a small number of times. In applications where most class labels are rare, such as language modelling, this can become a performance…

Machine Learning · Computer Science 2018-03-28 Jack W Rae , Chris Dyer , Peter Dayan , Timothy P Lillicrap

Deep learning has yielded state-of-the-art performance on many natural language processing tasks including named entity recognition (NER). However, this typically requires large amounts of labeled data. In this work, we demonstrate that the…

Computation and Language · Computer Science 2018-02-06 Yanyao Shen , Hyokun Yun , Zachary C. Lipton , Yakov Kronrod , Animashree Anandkumar

In Neural Networks (NN), Adaptive Activation Functions (AAF) have parameters that control the shapes of activation functions. These parameters are trained along with other parameters in the NN. AAFs have improved performance of Neural…

Computer Vision and Pattern Recognition · Computer Science 2016-08-24 Le Hou , Dimitris Samaras , Tahsin M. Kurc , Yi Gao , Joel H. Saltz