English
Related papers

Related papers: Ray-Tracing for Conditionally Activated Neural Net…

200 papers

Sparsely gated Mixture-of-Expert (MoE) has demonstrated its effectiveness in scaling up deep neural networks to an extreme scale. Despite that numerous efforts have been made to improve the performance of MoE from the model design or system…

Machine Learning · Computer Science 2023-02-21 Chang Chen , Min Li , Zhihua Wu , Dianhai Yu , Chao Yang

Time series forecasting models are increasingly scaled through large Transformer backbones, yet most existing approaches process all series through a shared dense computation path despite substantial heterogeneity in temporal structure.…

Machine Learning · Computer Science 2026-05-26 Rui Wang , Renhao Xue , Ray Razi , Huan Song , Hannah R. Marlowe

The Morris-Lecar (ML) model has applications to neuroscience and cognition. A simple network consisting of a pair of synaptically coupled ML neurons can exhibit a wide variety of deterministic behaviors including asymmetric amplitude state…

Dynamical Systems · Mathematics 2012-09-11 Karleigh Cameron , Marissa Saladin

Neural sequence-to-sequence models are well established for applications which can be cast as mapping a single input sequence into a single output sequence. In this work, we focus on one-to-many sequence transduction problems, such as…

Audio and Speech Processing · Electrical Eng. & Systems 2020-06-26 Jing Shi , Xuankai Chang , Pengcheng Guo , Shinji Watanabe , Yusuke Fujita , Jiaming Xu , Bo Xu , Lei Xie

We describe a novel family of models of multi- layer feedforward neural networks in which the activation functions are encoded via penalties in the training problem. Our approach is based on representing a non-decreasing activation function…

Machine Learning · Computer Science 2018-06-22 Armin Askari , Geoffrey Negiar , Rajiv Sambharya , Laurent El Ghaoui

Neural operators have emerged as an efficient paradigm for solving PDEs, overcoming the limitations of traditional numerical methods and significantly improving computational efficiency. However, due to the diversity and complexity of PDE…

Computer Vision and Pattern Recognition · Computer Science 2026-02-26 Dengdi Sun , Xiaoya Zhou , Xiao Wang , Hao Si , Wanli Lyu , Jin Tang , Bin Luo

Linear Mode Connectivity (LMC) is a notable phenomenon in the loss landscapes of neural networks, wherein independently trained models have been observed to be connected--up to permutation symmetries--by linear paths in parameter space…

Machine Learning · Computer Science 2025-10-28 Viet-Hoang Tran , Van Hoan Trinh , Khanh Vinh Bui , Tan M. Nguyen

Mixture-of-Experts (MoE) models have emerged as a dominant paradigm for efficient LLM scaling, yet adapting them to non-English downstream tasks remains challenging. Existing fine-tuning approaches treat MoE models as monolithic learners,…

Computation and Language · Computer Science 2026-05-28 Guanzhi Deng , Kuan Wu , Haibo Wang , Shing Yin Wong , Sichun Luo , Linqi Song

A neural network architecture is presented that exploits the multilevel properties of high-dimensional parameter-dependent partial differential equations, enabling an efficient approximation of parameter-to-solution maps, rivaling…

Machine Learning · Computer Science 2024-08-21 Janina Enrica Schütte , Martin Eigel

Neural models have shown promise in solving NP-hard graph combinatorial optimization (CO) problems. Once trained, they offer fast inference and reasonably high-quality solutions for in-distribution testing instances, but they generally fall…

Machine Learning · Computer Science 2025-11-26 Jialiang Li , Weitong Chen , Mingyu Guo

In machine learning, there is a fundamental trade-off between ease of optimization and expressive power. Neural Networks, in particular, have enormous expressive power and yet are notoriously challenging to train. The nature of that…

Machine Learning · Computer Science 2015-11-24 Diogo Almeida , Nate Sauder

This article investigates the effect of explicitly adding auxiliary algebraic trajectory information to neural networks for dynamical systems. We draw inspiration from the field of differential-algebraic equations and differential equations…

Machine Learning · Computer Science 2024-03-13 Tue Boesen , Eldad Haber , Uri Michael Ascher

The Mixture of Experts (MoE) architecture has become a fundamental building block in state-of-the-art large language models (LLMs), improving domain-specific expertise in LLMs and scaling model capacity without proportionally increasing…

Machine Learning · Computer Science 2026-05-13 Ankit Jyothish , Ali Jannesari , Aishwarya Sarkar , Joseph Zuber

Identifying a coupled dynamical system out of many plausible candidates, each of which could serve as the underlying generator of some observed measurements, is a profoundly ill posed problem that commonly arises when modelling real world…

Neurons and Cognition · Quantitative Biology 2019-09-17 Amirhossein Jafarian , Peter Zeidman , Vladimir Litvak , Karl Friston

Scaling large language models (LLMs) improves performance but significantly increases inference costs, with feed-forward networks (FFNs) consuming the majority of computational resources. While Mixture-of-Experts (MoE) architectures can…

Machine Learning · Computer Science 2026-04-24 Zehua Pei , Hui-Ling Zhen , Lancheng Zou , Xianzhi Yu , Wulong Liu , Sinno Jialin Pan , Mingxuan Yuan , Bei Yu

Efficiency, specialization, and adaptability to new data distributions are qualities that are hard to combine in current Large Language Models. The Mixture of Experts (MoE) architecture has been the focus of significant research because its…

Computation and Language · Computer Science 2024-08-29 Nikolas Gritsch , Qizhen Zhang , Acyr Locatelli , Sara Hooker , Ahmet Üstün

There is an implicit assumption that by unfolding recurrent neural networks (RNN) in finite time, the misspecification of choosing a zero value for the initial hidden state is mitigated by later time steps. This assumption has been shown to…

Machine Learning · Computer Science 2019-02-12 Sam Wenke , Jim Fleming

Neural network design has utilized flexible nonlinear processes which can mimic biological systems, but has suffered from a lack of traceability in the resulting network. Graphical probabilistic models ground network design in probabilistic…

Machine Learning · Computer Science 2015-06-19 Kenric P. Nelson , Madalina Barbu , Brian J. Scannell

Class-incremental learning (CIL) requires deep learning models to continuously acquire new knowledge from streaming data while preserving previously learned information. Recently, CIL based on pre-trained models (PTMs) has achieved…

Machine Learning · Computer Science 2025-06-16 Linjie Li , Zhenyu Wu , Yang Ji

This study introduces a novel expert generation method that dynamically reduces task and computational complexity without compromising predictive performance. It is based on a new hierarchical classification network topology that combines…

Machine Learning · Computer Science 2024-11-21 André Kelm , Niels Hannemann , Bruno Heberle , Lucas Schmidt , Tim Rolff , Christian Wilms , Ehsan Yaghoubi , Simone Frintrop
‹ Prev 1 8 9 10 Next ›