English
Related papers

Related papers: A Random-Matrix Criterion for Initializing Gated R…

200 papers

In past few years, various initialization schemes have been proposed. These schemes are glorot initialization, He initialization, initialization using orthogonal matrix, random walk method for initialization. Some of these methods stress on…

Machine Learning · Computer Science 2025-09-08 Vijay Pandey

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

Recently mean field theory has been successfully used to analyze properties of wide, random neural networks. It gave rise to a prescriptive theory for initializing feed-forward neural networks with orthogonal weights, which ensures that…

Machine Learning · Statistics 2019-06-05 Piotr A. Sokol , Il Memming Park

Reservoir computing(RC) is a brain-inspired computing framework that employs a transient dynamical system whose reaction to an input signal is transformed to a target output. One of the central problems in RC is to find a reliable reservoir…

Chaotic Dynamics · Physics 2020-08-26 Jaesung Choi , Pilwon Kim

State construction is important for learning in partially observable environments. A general purpose strategy for state construction is to learn the state update using a Recurrent Neural Network (RNN), which updates the internal state using…

Machine Learning · Computer Science 2021-02-03 Matthew Schlegel , Andrew Jacobsen , Zaheer Abbas , Andrew Patterson , Adam White , Martha White

The focus of this study is to investigate the impact of different initialization strategies for the weight matrix of Successor Features (SF) on learning efficiency and convergence in Reinforcement Learning (RL) agents. Using a grid-world…

Neurons and Cognition · Quantitative Biology 2024-02-08 Hyunsu Lee

We show that gating mechanisms in recurrent neural networks (RNNs) induce lag-dependent and direction-dependent effective learning rates, even when training uses a fixed, global step size. This behavior arises from a coupling between…

Machine Learning · Computer Science 2026-04-22 Lorenzo Livi

We present a unified theoretical framework connecting the first property of Deep Neural Collapse (DNC1) to the emergence of implicit low-rank bias in nonlinear networks trained with $L^2$ weight decay regularization. Our main contributions…

Machine Learning · Computer Science 2026-02-12 Emanuele Zangrando , Piero Deidda , Simone Brugiapaglia , Nicola Guglielmi , Francesco Tudisco

Due to its perceptual limitations, an agent may have too little information about the state of the environment to act optimally. In such cases, it is important to keep track of the observation history to uncover hidden state. Recent deep…

Machine Learning · Computer Science 2021-02-18 Miguel Suau , Jinke He , Elena Congeduti , Rolf A. N. Starre , Aleksander Czechowski , Frans A. Oliehoek

Reservoir computing - information processing based on untrained recurrent neural networks with random connections - is expected to depend on the nonlinear properties of the neurons and the resulting oscillatory, chaotic, or fixpoint…

Neural and Evolutionary Computing · Computer Science 2024-11-18 Claus Metzner , Achim Schilling , Andreas Maier , Patrick Krauss

Recent work has shown that Transformers' compositional generalization is governed by \emph{complexity control}, initialization scale and weight decay, which steers training toward low-complexity reasoning solutions rather than…

Machine Learning · Computer Science 2026-05-07 Sarwan Ali

The goal of this paper is to provide sufficient conditions for guaranteeing the Input-to-State Stability (ISS) and the Incremental Input-to-State Stability ({\delta}ISS) of Gated Recurrent Units (GRUs) neural networks. These conditions,…

Systems and Control · Electrical Eng. & Systems 2021-10-12 Fabio Bonassi , Marcello Farina , Riccardo Scattolini

Graph Neural Networks (GNNs) have demonstrated remarkable efficacy in handling graph-structured data; however, they exhibit failures after deployment, which can cause severe consequences. Hence, conducting thorough testing before deployment…

Software Engineering · Computer Science 2025-12-23 Lichen Yang , Qiang Wang , Zhonghao Yang , Daojing He , Yu Li

We propose a simultaneous learning and pruning algorithm capable of identifying and eliminating irrelevant structures in a neural network during the early stages of training. Thus, the computational cost of subsequent training iterations,…

Machine Learning · Computer Science 2023-01-16 Valentin Frank Ingmar Guenter , Athanasios Sideris

Recurrent Neural Networks (RNNs) frequently exhibit complicated dynamics, and their sensitivity to the initialization process often renders them notoriously hard to train. Recent works have shed light on such phenomena analyzing when…

Machine Learning · Computer Science 2022-10-12 Vaggos Chatziafratis , Ioannis Panageas , Clayton Sanford , Stelios Andrew Stavroulakis

The Recurrent Neural Networks and their variants have shown promising performances in sequence modeling tasks such as Natural Language Processing. These models, however, turn out to be impractical and difficult to train when exposed to very…

Computer Vision and Pattern Recognition · Computer Science 2017-07-07 Yinchong Yang , Denis Krompass , Volker Tresp

Motivated by the idea that criticality and universality of phase transitions might play a crucial role in achieving and sustaining learning and intelligent behaviour in biological and artificial networks, we analyse a theoretical and a…

Artificial Intelligence · Computer Science 2017-06-01 Dan Oprisa , Peter Toth

Post-training dropout based approaches achieve high sparsity and are well established means of deciphering problems relating to computational cost and overfitting in Neural Network architectures. Contrastingly, pruning at initialization is…

Neural and Evolutionary Computing · Computer Science 2022-09-07 Maham Haroon

Initialization of parameters in deep neural networks has been shown to have a big impact on the performance of the networks (Mishkin & Matas, 2015). The initialization scheme devised by He et al, allowed convolution activations to carry a…

Machine Learning · Computer Science 2017-02-28 Armen Aghajanyan

A physical neural network (PNN) has both the strong potential to solve machine learning tasks and intrinsic physical properties, such as high-speed computation and energy efficiency. Reservoir computing (RC) is an excellent framework for…

Chaotic Dynamics · Physics 2024-12-18 Tomoyuki Kubota , Yusuke Imai , Sumito Tsunegi , Kohei Nakajima