English
Related papers

Related papers: Learnability Window in Gated Recurrent Neural Netw…

200 papers

Deep neural networks (DNN) with a huge number of adjustable parameters remain largely black boxes. To shed light on the hidden layers of DNN, we study supervised learning by a DNN of width $N$ and depth $L$ consisting of $NL$ perceptrons…

Disordered Systems and Neural Networks · Physics 2023-08-01 Hajime Yoshino

Recurrent neural network grammars (RNNG) are a recently proposed probabilistic generative modeling family for natural language. They show state-of-the-art language modeling and parsing performance. We investigate what information they…

Computation and Language · Computer Science 2017-01-12 Adhiguna Kuncoro , Miguel Ballesteros , Lingpeng Kong , Chris Dyer , Graham Neubig , Noah A. Smith

This paper introduces a model-based approach for training feedback controllers for an autonomous agent operating in a highly nonlinear (albeit deterministic) environment. We desire the trained policy to ensure that the agent satisfies…

Systems and Control · Electrical Eng. & Systems 2024-08-29 Navid Hashemi , Bardh Hoxha , Danil Prokhorov , Georgios Fainekos , Jyotirmoy Deshmukh

A wide range of networks, including small-world topology, can be modelled by the connectivity $\gamma$, and randomness $\omega$ of the links. Both learning and attractor abilities of a neural network can be measured by the mutual…

Disordered Systems and Neural Networks · Physics 2007-05-23 D. Dominguez , K. Koroutchev , E. Serrano , F. B. Rodriguez

Recurrent neural network (RNN)'s architecture is a key factor influencing its performance. We propose algorithms to optimize hidden sizes under running time constraint. We convert the discrete optimization into a subset selection problem.…

Machine Learning · Statistics 2018-02-22 Junqi Jin , Ziang Yan , Kun Fu , Nan Jiang , Changshui Zhang

Two potential bottlenecks on the expressiveness of recurrent neural networks (RNNs) are their ability to store information about the task in their parameters, and to store information about the input history in their units. We show…

Machine Learning · Statistics 2017-03-06 Jasmine Collins , Jascha Sohl-Dickstein , David Sussillo

The optimality of Bayesian filtering relies on the completeness of prior models, while deep learning holds a distinct advantage in learning models from offline data. Nevertheless, the current fusion of these two methodologies remains…

Signal Processing · Electrical Eng. & Systems 2024-03-11 Shi Yan , Yan Liang , Le Zheng , Mingyang Fan , Xiaoxu Wang , Binglu Wang

Recently, methods have been developed to accurately predict the testing performance of a Deep Neural Network (DNN) on a particular task, given statistics of its underlying topological structure. However, further leveraging this newly found…

Computer Vision and Pattern Recognition · Computer Science 2021-12-01 Stuart Synakowski , Fabian Benitez-Quiroz , Aleix M. Martinez

Modern autoregressive models rely on attention, yet the Softmax full attention in Transformers scales quadratically with sequence length. Sliding Window Attention (SWA) achieves linear-time encoding/decoding by constraining the attention…

Machine Learning · Computer Science 2026-01-08 Jiaxu Liu , Yuhe Bai , Xiangyu Yin , Christos-Savvas Bouganis

Computational models of vision have traditionally been developed in a bottom-up fashion, by hierarchically composing a series of straightforward operations - i.e. convolution and pooling - with the aim of emulating simple and complex cells…

Computer Vision and Pattern Recognition · Computer Science 2022-03-23 Simone Azeglio , Simone Poetto , Luca Savant Aira , Marco Nurisso

Generative models trained on finite data face a fundamental tension: their score-matching or next-token objective converges to the empirical training distribution rather than the population distribution we seek to learn. Using rule-valid…

Machine Learning · Computer Science 2026-05-12 Binxu Wang , Emma Lucia Byrnes Finn , Bingbin Liu

Gate functions in recurrent models, such as an LSTM and GRU, play a central role in learning various time scales in modeling time series data by using a bounded activation function. However, it is difficult to train gates to capture…

Machine Learning · Computer Science 2022-10-05 Kentaro Ohno , Sekitoshi Kanai , Yasutoshi Ida

Most algorithms for decentralized learning employ a consensus or diffusion mechanism to drive agents to a common solution of a global optimization problem. Generally this takes the form of linear averaging, at a rate of contraction…

Optimization and Control · Mathematics 2024-06-07 Aaron Fainman , Stefan Vlaski

Dynamical systems describe how a physical system evolves over time. Physical processes can evolve faster or slower in different environmental conditions. We use time-warping as rescaling the time in a model of a physical system. This thesis…

Machine Learning · Computer Science 2026-05-12 Jonathon Hirschi

In this paper, we study novel neural network structures to better model long term dependency in sequential data. We propose to use more memory units to keep track of more preceding states in recurrent neural networks (RNNs), which are all…

Neural and Evolutionary Computing · Computer Science 2016-05-03 Rohollah Soltani , Hui Jiang

Learning on temporal graphs has become a central topic in graph representation learning, with numerous benchmarks indicating the strong performance of state-of-the-art models. However, recent work has raised concerns about the reliability…

Machine Learning · Computer Science 2026-04-03 Abigail J. Hayes , Tobias Schumacher , Markus Strohmaier

Growing evidence suggests that synaptic weights in the brain follow heavy-tailed distributions, yet most theoretical analyses of recurrent neural networks (RNNs) assume Gaussian connectivity. We systematically study the activity of RNNs…

Neurons and Cognition · Quantitative Biology 2025-10-27 Yi Xie , Stefan Mihalas , Łukasz Kuśmierz

Graph neural networks (GNNs) are the most widely adopted model in graph-structured data oriented learning and representation. Despite their extraordinary success in real-world applications, understanding their working mechanism by theory is…

Machine Learning · Computer Science 2023-05-16 Huayi Tang , Yong Liu

The learning dynamics of deep neural networks are subject to controversy. Using the information bottleneck (IB) theory separate fitting and compression phases have been put forward but have since been heavily debated. We approach learning…

Machine Learning · Computer Science 2022-02-18 Johannes Schneider

Recurrent neural networks (RNNs) for reinforcement learning (RL) have shown distinct advantages, e.g., solving memory-dependent tasks and meta-learning. However, little effort has been spent on improving RNN architectures and on…

Machine Learning · Computer Science 2019-11-27 Dongqi Han , Kenji Doya , Jun Tani