English
Related papers

Related papers: mGRADE: Minimal Recurrent Gating Meets Delay Convo…

200 papers

We revisit the efficacy of simple, real-valued embedding models for knowledge graph completion and introduce RelatE, an interpretable and modular method that efficiently integrates dual representations for entities and relations. RelatE…

Computation and Language · Computer Science 2025-05-27 Abhijit Chakraborty , Chahana Dahal , Ashutosh Balasubramaniam , Tejas Anvekar , Vivek Gupta

In this short note, we present an extension of long short-term memory (LSTM) neural networks to using a depth gate to connect memory cells of adjacent layers. Doing so introduces a linear dependence between lower and upper layer recurrent…

Neural and Evolutionary Computing · Computer Science 2015-08-26 Kaisheng Yao , Trevor Cohn , Katerina Vylomova , Kevin Duh , Chris Dyer

In this work, we propose a novel recurrent neural network (RNN) architecture. The proposed RNN, gated-feedback RNN (GF-RNN), extends the existing approach of stacking multiple recurrent layers by allowing and controlling signals flowing…

Neural and Evolutionary Computing · Computer Science 2015-06-18 Junyoung Chung , Caglar Gulcehre , Kyunghyun Cho , Yoshua Bengio

Recurrent neural networks (RNNs) such as long short-term memory and gated recurrent units are pivotal building blocks across a broad spectrum of sequence modeling problems. This paper proposes a recurrently controlled recurrent network…

Computation and Language · Computer Science 2018-11-27 Yi Tay , Luu Anh Tuan , Siu Cheung Hui

Convolution is a critical component in modern deep neural networks, thus several algorithms for convolution have been developed. Direct convolution is simple but suffers from poor performance. As an alternative, multiple indirect methods…

Machine Learning · Computer Science 2017-06-22 Minsik Cho , Daniel Brand

Spiking neural networks (SNNs) inherently rely on the timing of signals for representing and processing information. Incorporating trainable transmission delays, alongside synaptic weights, is crucial for shaping these temporal dynamics.…

Neural and Evolutionary Computing · Computer Science 2025-04-17 Julian Göltz , Jimmy Weber , Laura Kriener , Sebastian Billaudelle , Peter Lake , Johannes Schemmel , Melika Payvand , Mihai A. Petrovici

Radar sensors offer power-efficient solutions for always-on smart devices, but processing the data streams on resource-constrained embedded platforms remains challenging. This paper presents novel techniques that leverage the temporal…

Machine Learning · Computer Science 2023-09-13 Max Sponner , Julius Ott , Lorenzo Servadei , Bernd Waschneck , Robert Wille , Akash Kumar

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

Recurrent neural architectures such as LSTM and GRU remain widely used in sequence modeling, but they continue to face two core limitations: redundant gate-specific parameters and reduced ability to retain information across long temporal…

Machine Learning · Computer Science 2025-12-09 Isaac Kofi Nti

Multi-step retrieval-augmented generation (RAG) has become a widely adopted strategy for enhancing large language models (LLMs) on tasks that demand global comprehension and intensive reasoning. Although many RAG systems incorporate a…

Computation and Language · Computer Science 2026-05-28 Chulun Zhou , Chunkang Zhang , Guoxin Yu , Fandong Meng , Jie Zhou , Wai Lam , Mo Yu

Recurrent neural networks can learn complex transduction problems that require maintaining and actively exploiting a memory of their inputs. Such models traditionally consider memory and input-output functionalities indissolubly entangled.…

Machine Learning · Computer Science 2018-11-09 Davide Bacciu , Antonio Carta , Alessandro Sperduti

Designing deep neural networks is an art that often involves an expensive search over candidate architectures. To overcome this for recurrent neural nets (RNNs), we establish a connection between the hidden state dynamics in an RNN and…

Machine Learning · Computer Science 2021-12-14 Tan M. Nguyen , Richard G. Baraniuk , Andrea L. Bertozzi , Stanley J. Osher , Bao Wang

In this paper we compare different types of recurrent units in recurrent neural networks (RNNs). Especially, we focus on more sophisticated units that implement a gating mechanism, such as a long short-term memory (LSTM) unit and a recently…

Neural and Evolutionary Computing · Computer Science 2014-12-12 Junyoung Chung , Caglar Gulcehre , KyungHyun Cho , Yoshua Bengio

Memory retrieval in agentic large language model (LLM) systems is often treated as a static lookup problem, relying on flat vector search or fixed binary relational graphs. However, fixed graph structures cannot capture the varying…

Artificial Intelligence · Computer Science 2026-05-12 Dongming Jiang , Yi Li , Guanpeng Li , Qiannan Li , Bingzhe Li

Stochastic Gradient Descent (SGD) is a fundamental algorithm in machine learning, representing the optimization backbone for training several classic models, from regression to neural networks. Given the recent practical focus on…

Distributed, Parallel, and Cluster Computing · Computer Science 2018-06-25 Dan Alistarh , Christopher De Sa , Nikola Konstantinov

The pervasive "memory wall" bottleneck is significantly amplified in modern large-scale Mixture-of-Experts (MoE) architectures. MoE's inherent architectural sparsity leads to sparse arithmetic compute and also introduces substantial…

Machine Learning · Computer Science 2026-01-12 Jiyuan Zhang , Yining Liu , Siqi Yan , Lisen Deng , Jennifer Cao , Shuqi Yang , Min Ni , Bi Xue , Shen Li

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

Dissipative cognitive architectures maintain computation through continuous energy expenditure, where units that exhaust their energy are stochastically replaced with fresh random state. This creates a fundamental challenge: how can…

Neural and Evolutionary Computing · Computer Science 2026-03-31 Jianwei Lou

Transformers face a quadratic bottleneck in attention when scaling to long contexts. Recent approaches introduce recurrent memory to extend context beyond the current window, yet these often face a fundamental trade-off between theoretical…

Machine Learning · Computer Science 2026-02-13 Yunchong Song , Jushi Kai , Liming Lu , Kaixi Qiu , Zhouhan Lin

LSTMs were introduced to combat vanishing gradients in simple RNNs by augmenting them with gated additive recurrent connections. We present an alternative view to explain the success of LSTMs: the gates themselves are versatile recurrent…

Computation and Language · Computer Science 2018-05-11 Omer Levy , Kenton Lee , Nicholas FitzGerald , Luke Zettlemoyer