Imagen de Portada

Gated recurrent neural networks discover attention

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zucchet, Nicolas, Kobayashi, Seijin, Akram, Yassir, von Oswald, Johannes, Larcher, Maxime, Steger, Angelika, Sacramento, João
Formato:	Preprint
Publicado:	2023
Materias:	Machine Learning Neural and Evolutionary Computing
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Discovering modular solutions that generalize compositionally
por: Schug, Simon, et al.
Publicado: (2023)

When can transformers compositionally generalize in-context?
por: Kobayashi, Seijin, et al.
Publicado: (2024)

Teaching signal synchronization in deep neural networks with prospective neurons
por: Zucchet, Nicoas, et al.
Publicado: (2025)

Learning Randomized Algorithms with Transformers
por: von Oswald, Johannes, et al.
Publicado: (2024)

The emergence of sparse attention: impact of data distribution and benefits of repetition
por: Zucchet, Nicolas, et al.
Publicado: (2025)

Gate-level boolean evolutionary geometric attention neural networks
por: Shi, Xianshuai, et al.
Publicado: (2025)

Scaling can lead to compositional generalization
por: Redhardt, Florian, et al.
Publicado: (2025)

Universality of reservoir systems with recurrent neural networks
por: Yasumoto, Hiroki, et al.
Publicado: (2024)

Weight decay induces low-rank attention layers
por: Kobayashi, Seijin, et al.
Publicado: (2024)

Spike-based computation using classical recurrent neural networks
por: De Geeter, Florent, et al.
Publicado: (2023)

Sufficient conditions for offline reactivation in recurrent neural networks
por: Krishna, Nanda H., et al.
Publicado: (2025)

Differentiable architecture search with multi-dimensional attention for spiking neural networks
por: Man, Yilei, et al.
Publicado: (2024)

DelRec: learning delays in recurrent spiking neural networks
por: Queant, Alexandre, et al.
Publicado: (2025)

OneMax is not the Easiest Function for Fitness Improvements
por: Kaufmann, Marc, et al.
Publicado: (2022)

Gated recurrent neural network with TPE Bayesian optimization for enhancing stock index prediction accuracy
por: Dinda, Bivas
Publicado: (2024)

When Spiking neural networks meet temporal attention image decoding and adaptive spiking neuron
por: Qiu, Xuerui, et al.
Publicado: (2024)

Hardest Monotone Functions for Evolutionary Algorithms
por: Kaufmann, Marc, et al.
Publicado: (2023)

Structure of activity in multiregion recurrent neural networks
por: Clark, David G., et al.
Publicado: (2024)

Predicting concentration levels of air pollutants by transfer learning and recurrent neural network
por: Fong, Iat Hang, et al.
Publicado: (2025)

Connectivity structure and dynamics of nonlinear recurrent neural networks
por: Clark, David G., et al.
Publicado: (2024)

Investigating the generative dynamics of energy-based neural networks
por: Tausani, Lorenzo, et al.
Publicado: (2023)

Learning fast changing slow in spiking neural networks
por: Capone, Cristiano, et al.
Publicado: (2024)

Designing deep neural networks for driver intention recognition
por: Vellenga, Koen, et al.
Publicado: (2024)

Learning richness modulates equality reasoning in neural networks
por: Tong, William L., et al.
Publicado: (2025)

The late-stage training dynamics of (stochastic) subgradient descent on homogeneous neural networks
por: Schechtman, Sholom, et al.
Publicado: (2025)

Improved weight initialization for deep and narrow feedforward neural network
por: Lee, Hyunwoo, et al.
Publicado: (2023)

Three factor delay learning rules for spiking neural networks
por: Vassallo, Luke, et al.
Publicado: (2026)

Hypercomplex neural network in time series forecasting of stock data
por: Kycia, Radosław, et al.
Publicado: (2024)

Flexible inference for animal learning rules using neural networks
por: Liu, Yuhan Helena, et al.
Publicado: (2025)

Optimal feature rescaling in machine learning based on neural networks
por: Vitrò, Federico Maria, et al.
Publicado: (2024)

Fast gradient-free activation maximization for neurons in spiking neural networks
por: Pospelov, Nikita, et al.
Publicado: (2023)

Application-oriented automatic hyperparameter optimization for spiking neural network prototyping
por: Fra, Vittorio
Publicado: (2025)

A rationale from frequency perspective for grokking in training neural network
por: Zhou, Zhangchen, et al.
Publicado: (2024)

Gradient-based inference of abstract task representations for generalization in neural networks
por: Hummos, Ali, et al.
Publicado: (2024)

Discovering alternative solutions beyond the simplicity bias in recurrent neural networks
por: Qian, William, et al.
Publicado: (2025)

Prototype-based interpretation of the functionality of neurons in winner-take-all neural networks
por: Sabzevar, Ramin Zarei, et al.
Publicado: (2020)

Impact of leaky dynamics on predictive path integration accuracy in recurrent neural networks
por: Zhang, Yanlin, et al.
Publicado: (2026)

gFlora: a topology-aware method to discover functional co-response groups in soil microbial communities
por: Chen, Nan, et al.
Publicado: (2024)

How noise affects memory in linear recurrent networks
por: Guan, JingChuan, et al.
Publicado: (2024)

Iteration over event space in time-to-first-spike spiking neural networks for Twitter bot classification
por: Pabian, Mateusz, et al.
Publicado: (2024)