English
Related papers

Related papers: Expand Neurons, Not Parameters

200 papers

We investigate the complexity of deep neural networks through the lens of functional equivalence, which posits that different parameterizations can yield the same network function. Leveraging the equivalence property, we present a novel…

Machine Learning · Computer Science 2024-05-17 Guohao Shen

It has been observed in practical applications and in theoretical analysis that over-parametrization helps to find good minima in neural network training. Similarly, in this article we study widening and deepening neural networks by a…

Numerical Analysis · Mathematics 2020-02-06 G. Welper

Fragmentation methods such as the many-body expansion (MBE) are a common strategy to model large systems by partitioning energies into a hierarchy of decreasingly significant contributions. The number of fragments required for chemical…

Chemical Physics · Physics 2017-09-13 Kun Yao , John E. Herr , John Parkhill

Inspired by neuronal diversity in the biological neural system, a plethora of studies proposed to design novel types of artificial neurons and introduce neuronal diversity into artificial neural networks. Recently proposed quadratic neuron,…

Machine Learning · Computer Science 2023-03-14 Feng-Lei Fan , Hang-Cheng Dong , Zhongming Wu , Lecheng Ruan , Tieyong Zeng , Yiming Cui , Jing-Xiao Liao

Neural Posterior Estimation (NPE) enables rapid parameter inference for complex simulators with intractable likelihoods. NPE trains an inference network to estimate a probability density over parameters given data, typically assumed to be…

Machine Learning · Computer Science 2026-05-14 Jan Boelts , Cornelius Schröder , Jonas Beck , Jakob H. Macke , Michael Deistler , Daniel Gedon

Physics-Informed Neural Networks (PINNs) seek to solve partial differential equations (PDEs) with deep learning. Mainstream approaches that deploy fully-connected multi-layer deep learning architectures require prolonged training to achieve…

Machine Learning · Computer Science 2025-12-16 Shaghayegh Fazliani , Zachary Frangella , Madeleine Udell

In federated learning problems, data is scattered across different servers and exchanging or pooling it is often impractical or prohibited. We develop a Bayesian nonparametric framework for federated learning with neural networks. Each data…

Neural networks with a large number of parameters admit a mean-field description, which has recently served as a theoretical explanation for the favorable training properties of "overparameterized" models. In this regime, gradient descent…

Machine Learning · Statistics 2019-03-28 Grant Rotskoff , Samy Jelassi , Joan Bruna , Eric Vanden-Eijnden

Federated learning (FL) has emerged as a promising paradigm for enabling the collaborative training of models without centralized access to the raw data on local devices. In the typical FL paradigm (e.g., FedAvg), model weights are sent to…

Machine Learning · Computer Science 2024-12-25 Guangyu Sun , Umar Khalid , Matias Mendieta , Pu Wang , Chen Chen

We re-evaluate the standard practice of sharing weights between input and output embeddings in state-of-the-art pre-trained language models. We show that decoupled embeddings provide increased modeling flexibility, allowing us to…

Computation and Language · Computer Science 2020-10-27 Hyung Won Chung , Thibault Févry , Henry Tsai , Melvin Johnson , Sebastian Ruder

The firing dynamics of biological neurons in mathematical models is often determined by the model's parameters, representing the neurons' underlying properties. The parameter estimation problem seeks to recover those parameters of a single…

Neurons and Cognition · Quantitative Biology 2022-10-05 Long Le , Yao Li

Recently, emergence has received widespread attention from the research community along with the success of large-scale models. Different from the literature, we hypothesize a key factor that promotes the performance during the increase of…

Machine Learning · Computer Science 2024-06-21 Jiachuan Wang , Shimin Di , Lei Chen , Charles Wang Wai Ng

Neural networks have proven to be extremely powerful tools for modern artificial intelligence applications, but computational and storage complexity remain limiting factors. This paper presents two compatible contributions towards reducing…

Machine Learning · Computer Science 2024-10-30 Sourya Dey , Kuan-Wen Huang , Peter A. Beerel , Keith M. Chugg

Physics-informed neural networks (PINNs) have recently become a powerful tool for solving partial differential equations (PDEs). However, finding a set of neural network parameters that lead to fulfilling a PDE can be challenging and…

Machine Learning · Computer Science 2023-04-12 Aleksandr Dekhovich , Marcel H. F. Sluiter , David M. J. Tax , Miguel A. Bessa

Feature selection reduces the dimensionality of data by identifying a subset of the most informative features. In this paper, we propose an innovative framework for unsupervised feature selection, called fractal autoencoders (FAE). It…

Machine Learning · Computer Science 2022-01-06 Xinxing Wu , Qiang Cheng

Mixture of Experts (MoE) has become a mainstream architecture for building Large Language Models (LLMs) by reducing per-token computation while enabling model scaling. It can be viewed as partitioning a large Feed-Forward Network (FFN) at…

Machine Learning · Computer Science 2025-08-27 Weilin Cai , Le Qin , Shwai He , Junwei Cui , Ang Li , Jiayi Huang

Spiking Neural Networks (SNNs) compute in an event-based matter to achieve a more efficient computation than standard Neural Networks. In SNNs, neuronal outputs (i.e. activations) are not encoded with real-valued activations but with…

Hardware Architecture · Computer Science 2023-08-08 Jan Sommer , M. Akif Özkan , Oliver Keszocze , Jürgen Teich

Considering the use of Fully Connected (FC) layer limits the performance of Convolutional Neural Networks (CNNs), this paper develops a method to improve the coupling between the convolution layer and the FC layer by reducing the noise in…

Machine Learning · Computer Science 2019-01-08 Yang Liu , Qiang Qu , Chao Gao

The Mixture-of-Experts (MoE) architecture enables a significant increase in the total number of model parameters with minimal computational overhead. However, it is not clear what performance tradeoffs, if any, exist between MoEs and…

Modeling the behavior of coupled networks is challenging due to their intricate dynamics. For example in neuroscience, it is of critical importance to understand the relationship between the functional neural processes and anatomical…

Machine Learning · Computer Science 2021-04-20 Hongyuan You , Sikun Lin , Ambuj K. Singh