English
Related papers

Related papers: Expand Neurons, Not Parameters

200 papers

Weighted summation has remained the default input aggregation mechanism in artificial neurons since the earliest neural network models. While computationally efficient, this design implicitly behaves like a mean-based estimator and is…

Machine Learning · Computer Science 2026-03-23 Berke Deniz Bozyigit

Existing Machine Translation (MT) research often suggests a single, fixed set of hyperparameters for word segmentation models, symmetric Byte Pair Encoding (BPE), which applies the same number of merge operations (NMO) to train tokenizers…

Computation and Language · Computer Science 2026-02-16 Saumitra Yadav , Manish Shrivastava

Hypercomplex neural networks have proven to reduce the overall number of parameters while ensuring valuable performance by leveraging the properties of Clifford algebras. Recently, hypercomplex linear layers have been further improved by…

Machine Learning · Computer Science 2022-12-16 Eleonora Grassucci , Aston Zhang , Danilo Comminiello

Many state-of-the-art results obtained with deep networks are achieved with the largest models that could be trained, and if more computation power was available, we might be able to exploit much larger datasets in order to improve…

Machine Learning · Statistics 2014-07-01 Kyunghyun Cho , Yoshua Bengio

Recently, researchers have utilized neural networks to accurately solve partial differential equations (PDEs), enabling the mesh-free method for scientific computation. Unfortunately, the network performance drops when encountering a high…

Machine Learning · Computer Science 2021-09-29 Pongpisit Thanasutives , Masayuki Numao , Ken-ichi Fukui

Neural networks have achieved state of the art performance across a wide variety of machine learning tasks, often with large and computation-heavy models. Inducing sparseness as a way to reduce the memory and computation footprint of these…

Machine Learning · Computer Science 2022-10-21 Amir Hadifar , Johannes Deleu , Chris Develder , Thomas Demeester

Ensemble methods are commonly used to enhance the generalization performance of machine learning models. However, they present a challenge in deep learning systems due to the high computational overhead required to train an ensemble of deep…

Machine Learning · Computer Science 2023-05-24 Hao Guo , Jiyong Jin , Bin Liu

Neural networks commonly employ the McCulloch-Pitts neuron model, which is a linear model followed by a point-wise non-linear activation. Various researchers have already advanced inherently non-linear neuron models, such as quadratic…

Computer Vision and Pattern Recognition · Computer Science 2026-01-08 Onur Keleş , A. Murat Tekalp

Representation learning on graphs has emerged as a powerful mechanism to automate feature vector generation for downstream machine learning tasks. The advances in representation on graphs have centered on both homogeneous and heterogeneous…

Machine Learning · Statistics 2020-11-23 Piotr Bielak , Kamil Tagowski , Maciej Falkiewicz , Tomasz Kajdanowicz , Nitesh V. Chawla

Neural networks based on metric recognition methods have a strictly determined architecture. Number of neurons, connections, as well as weights and thresholds values are calculated analytically, based on the initial conditions of tasks:…

Neural and Evolutionary Computing · Computer Science 2025-06-10 Polad Geidarov

Network pruning focuses on algorithms that aim to reduce a given model's computational cost by removing a subset of its parameters while having minimal impact on performance. Throughout the last decade, the most widely used pruning paradigm…

Machine Learning · Computer Science 2025-11-11 Elia Cunegatti , Leonardo Lucio Custode , Giovanni Iacca

A common method in training neural networks is to initialize all the weights to be independent Gaussian vectors. We observe that by instead initializing the weights into independent pairs, where each pair consists of two identical Gaussian…

Machine Learning · Computer Science 2022-06-28 Alexander Munteanu , Simon Omlor , Zhao Song , David P. Woodruff

Recently, there have been increasing demands to construct compact deep architectures to remove unnecessary redundancy and to improve the inference speed. While many recent works focus on reducing the redundancy by eliminating unneeded…

Computer Vision and Pattern Recognition · Computer Science 2018-03-28 Eunwoo Kim , Chanho Ahn , Songhwai Oh

Network pruning is widely used to lighten and accelerate neural network models. Structured network pruning discards the whole neuron or filter, leading to accuracy loss. In this work, we propose a novel concept of neuron merging applicable…

Computer Vision and Pattern Recognition · Computer Science 2020-10-27 Woojeong Kim , Suhyun Kim , Mincheol Park , Geonseok Jeon

Though there are some works on improving distributed word representations using lexicons, the improper overfitting of the words that have multiple meanings is a remaining issue deteriorating the learning when lexicons are used, which needs…

Computation and Language · Computer Science 2017-03-10 Yuanzhi Ke , Masafumi Hagiwara

Deep neural networks have usually to be compressed and accelerated for their usage in low-power, e.g. mobile, devices. Recently, massively-parallel hardware accelerators were developed that offer high throughput and low latency at low power…

Machine Learning · Computer Science 2021-08-04 Thomas Pfeil

In biological evolution complex neural structures grow from a handful of cellular ingredients. As genomes in nature are bounded in size, this complexity is achieved by a growth process where cells communicate locally to decide whether to…

Neural and Evolutionary Computing · Computer Science 2024-05-15 Eleni Nisioti , Erwan Plantec , Milton Montero , Joachim Winther Pedersen , Sebastian Risi

Deep Neural nets (NNs) with millions of parameters are at the heart of many state-of-the-art computer vision systems today. However, recent works have shown that much smaller models can achieve similar levels of performance. In this work,…

Computer Vision and Pattern Recognition · Computer Science 2015-07-23 Suraj Srinivas , R. Venkatesh Babu

Neuro-encoded expression programming(NEEP) that aims to offer a novel continuous representation of combinatorial encoding for genetic programming methods is proposed in this paper. Genetic programming with linear representation uses…

Neural and Evolutionary Computing · Computer Science 2021-04-12 Aftab Anjum , Fengyang Sun , Lin Wang , Jeff Orchard

Designing an optimal deep neural network for a given task is important and challenging in many machine learning applications. To address this issue, we introduce a self-adaptive algorithm: the adaptive network enhancement (ANE) method,…

Numerical Analysis · Mathematics 2022-03-02 Zhiqiang Cai , Jingshuang Chen , Min Liu