English
Related papers

Related papers: Parametric Rectified Power Sigmoid Units: Learning…

200 papers

Previous research has explored the computational expressivity of Transformer models in simulating Boolean circuits or Turing machines. However, the learnability of these simulators from observational data has remained an open question. Our…

Machine Learning · Computer Science 2025-10-27 Morris Yau , Ekin Akyürek , Jiayuan Mao , Joshua B. Tenenbaum , Stefanie Jegelka , Jacob Andreas

This paper introduces a meta-learning approach for parameterized pseudo-differential operators with deep neural networks. With the help of the nonstandard wavelet form, the pseudo-differential operators can be approximated in a compressed…

Numerical Analysis · Mathematics 2020-02-26 Jordi Feliu-Faba , Yuwei Fan , Lexing Ying

Activation functions play a central role in neural networks by shaping internal representations. Recently, learning binary activation representations has attracted significant attention due to their advantages in computational and memory…

Machine Learning · Computer Science 2026-05-13 Seokhun Park , Choeun Kim , Kwanho Lee , Sehyun Park , Insung Kong , Yongdai Kim

Standard meta-learning for representation learning aims to find a common representation to be shared across multiple tasks. The effectiveness of these methods is often limited when the nuances of the tasks' distribution cannot be captured…

Machine Learning · Computer Science 2021-03-31 Giulia Denevi , Massimiliano Pontil , Carlo Ciliberto

The recent success of Transformers in the language domain has motivated adapting it to a multimodal setting, where a new visual model is trained in tandem with an already pretrained language model. However, due to the excessive memory…

Computer Vision and Pattern Recognition · Computer Science 2021-09-23 Sangho Lee , Youngjae Yu , Gunhee Kim , Thomas Breuel , Jan Kautz , Yale Song

Many methods have been proposed to solve the domain adaptation problem recently. However, the success of them implicitly funds on the assumption that the information of domains are fully transferrable. If the assumption is not satisfied,…

Computer Vision and Pattern Recognition · Computer Science 2018-07-10 Hoang Tran Vu , Ching-Chun Huang

Recurrent neural networks are extremely powerful yet hard to train. One of their issues is the vanishing gradient problem, whereby propagation of training signals may be exponentially attenuated, freezing training. Use of orthogonal or…

Machine Learning · Computer Science 2023-02-16 Marcelo O. Magnasco

A central challenge in reinforcement learning (RL) is to learn models that generalize beyond the tasks on which they are trained, a goal traditionally pursued through multi-task and meta RL. Recently, transformer architectures have emerged…

Machine Learning · Computer Science 2026-05-12 Bowen He , Juncheng Dong , Lin Lin , Xiang Cheng

Parameter transfer is a central paradigm in transfer learning, enabling knowledge reuse across tasks and domains by sharing model parameters between upstream and downstream models. However, when only a subset of parameters from the upstream…

Machine Learning · Computer Science 2026-01-08 Hua Yuan , Xuran Meng , Qiufeng Wang , Shiyu Xia , Ning Xu , Xu Yang , Jing Wang , Xin Geng , Yong Rui

Artificial neural networks used for reinforcement learning are structurally rigid, meaning that each optimized parameter of the network is tied to its specific placement in the network structure. It also means that a network only works with…

Neural and Evolutionary Computing · Computer Science 2024-05-20 Joachim Winther Pedersen , Erwan Plantec , Eleni Nisioti , Milton Montero , Sebastian Risi

This paper analyzes representations of continuous piecewise linear functions with infinite width, finite cost shallow neural networks using the rectified linear unit (ReLU) as an activation function. Through its integral representation, a…

Machine Learning · Computer Science 2023-09-26 Sarah McCarty

Existing approaches to combine both additive and multiplicative neural units either use a fixed assignment of operations or require discrete optimization to determine what function a neuron should perform. However, this leads to an…

Machine Learning · Computer Science 2016-04-14 Wiebke Köpp , Patrick van der Smagt , Sebastian Urban

In neural networks literature, there is a strong interest in identifying and defining activation functions which can improve neural network performance. In recent years there has been a renovated interest of the scientific community in…

Machine Learning · Computer Science 2021-03-01 Andrea Apicella , Francesco Donnarumma , Francesco Isgrò , Roberto Prevete

Activation function is a key component in deep learning that performs non-linear mappings between the inputs and outputs. Rectified Linear Unit (ReLU) has been the most popular activation function across the deep learning community.…

Machine Learning · Computer Science 2022-03-01 Hock Hung Chieng , Noorhaniza Wahid , Pauline Ong

Deep neural networks still struggle on long-tailed image datasets, and one of the reasons is that the imbalance of training data across categories leads to the imbalance of trained model parameters. Motivated by the empirical findings that…

Computer Vision and Pattern Recognition · Computer Science 2022-12-06 Haoxuan Wang , Junchi Yan

Neuro-symbolic reinforcement learning (NS-RL) has emerged as a promising paradigm for explainable decision-making, characterized by the interpretability of symbolic policies. NS-RL entails structured state representations for tasks with…

Artificial Intelligence · Computer Science 2024-06-14 Lirui Luo , Guoxi Zhang , Hongming Xu , Yaodong Yang , Cong Fang , Qing Li

Based on recent advancements in using machine learning for classical density functional theory for systems with one-dimensional, planar inhomogeneities, we propose a machine learning model for application in two dimensions (2D) akin to…

Statistical Mechanics · Physics 2025-05-22 Felix Glitsch , Jens Weimar , Martin Oettel

Realization of deep learning with coherent optical field has attracted remarkably attentions presently, which benefits on the fact that optical matrix manipulation can be executed at speed of light with inherent parallel computation as well…

Signal Processing · Electrical Eng. & Systems 2020-03-19 Yong-Liang Xiao , Rongguang Liang , Jianxin Zhong , Xianyu Su , Zhisheng You

Existing deep learning models may encounter great challenges in handling graph structured data. In this paper, we introduce a new deep learning model for graph data specifically, namely the deep loopy neural network. Significantly different…

Machine Learning · Computer Science 2019-09-06 Jiawei Zhang

To make progress in science, we often build abstract representations of physical systems that meaningfully encode information about the systems. The representations learnt by most current machine learning techniques reflect statistical…