English
Related papers

Related papers: Lie-Access Neural Turing Machines

200 papers

While linear attention architectures offer efficient inference, compressing unbounded history into a fixed-size memory inherently limits expressivity and causes information loss. To address this limitation, we introduce Random Access Memory…

Machine Learning · Computer Science 2026-02-13 Kaicheng Xiao , Haotian Li , Liran Dong , Guoliang Xing

In the classical RAM, we have the following useful property. If we have an algorithm that uses $M$ memory cells throughout its execution, and in addition is sparse, in the sense that, at any point in time, only $m$ out of $M$ cells will be…

Quantum Physics · Physics 2022-12-22 Harry Buhrman , Bruno Loff , Subhasree Patro , Florian Speelman

We propose Token Turing Machines (TTM), a sequential, autoregressive Transformer model with memory for real-world sequential visual understanding. Our model is inspired by the seminal Neural Turing Machine, and has an external memory…

Reason and inference require process as well as memory skills by humans. Neural networks are able to process tasks like image recognition (better than humans) but in memory aspects are still limited (by attention mechanism, size). Recurrent…

Machine Learning · Computer Science 2017-03-03 Amit Sahu

Neural networks augmented with external memory have the ability to learn algorithmic solutions to complex tasks. These models appear promising for applications such as language modeling and machine translation. However, they scale poorly in…

Machine Learning · Computer Science 2016-10-31 Jack W Rae , Jonathan J Hunt , Tim Harley , Ivo Danihelka , Andrew Senior , Greg Wayne , Alex Graves , Timothy P Lillicrap

The input/output complexity, which is the complexity of data exchange between the main memory and the external memory, has been elaborately studied by a lot of former researchers. However, the existing works failed to consider the…

Computational Complexity · Computer Science 2022-08-23 Hengzhao Ma , Jianzhong Li , Xiangyu Gao , Tianpeng Gao

We propose a novel perspective of the attention mechanism by reinventing it as a memory architecture for neural networks, namely Neural Attention Memory (NAM). NAM is a memory structure that is both readable and writable via differentiable…

Machine Learning · Computer Science 2023-10-17 Hyoungwook Nam , Seung Byum Seo

Recent developments in Language Models (LMs) have shown their effectiveness in NLP tasks, particularly in knowledge-intensive tasks. However, the mechanisms underlying knowledge storage and memory access within their parameters remain…

Computation and Language · Computer Science 2024-07-23 Tongyao Zhu , Qian Liu , Liang Pang , Zhengbao Jiang , Min-Yen Kan , Min Lin

The algorithm of brain learning and memory is still undetermined. The backpropagation algorithm of artificial neural networks was thought not suitable for brain cortex, and there is a lack of algorithm for memory engram. We designed a brain…

Neural and Evolutionary Computing · Computer Science 2020-10-29 Yifei Mao

We propose Lie group embedded dynamical neural networks (LieEDNN) and the corresponding learning algorithms based on gradient descent and metric projection on smooth manifold, where we treat Lie group as an intrinsic representation for…

Machine Learning · Computer Science 2026-05-27 Tianwei Wang , Bryan Chen , Qian Zuo , Qiyue Xia , Xin Li , Wei Pang

Recurrent neural network is a powerful model that learns temporal patterns in sequential data. For a long time, it was believed that recurrent networks are difficult to train using simple optimizers, such as stochastic gradient descent, due…

Neural and Evolutionary Computing · Computer Science 2015-04-20 Tomas Mikolov , Armand Joulin , Sumit Chopra , Michael Mathieu , Marc'Aurelio Ranzato

Recent developments within memory-augmented neural networks have solved sequential problems requiring long-term memory, which are intractable for traditional neural networks. However, current approaches still struggle to scale to large…

Artificial Intelligence · Computer Science 2017-10-16 Jakob Merrild , Mikkel Angaju Rasmussen , Sebastian Risi

This paper presents a new family of backpropagation-free neural architectures, Gated Linear Networks (GLNs). What distinguishes GLNs from contemporary neural networks is the distributed and local nature of their credit assignment mechanism;…

We investigate time-dependent data analysis from the perspective of recurrent kernel machines, from which models with hidden units and gated memory cells arise naturally. By considering dynamic gating of the memory cell, a model closely…

Machine Learning · Statistics 2019-10-11 Kevin J Liang , Guoyin Wang , Yitong Li , Ricardo Henao , Lawrence Carin

Handling orientations of robots and objects is a crucial aspect of many applications. Yet, ever so often, there is a lack of mathematical correctness when dealing with orientations, especially in learning pipelines involving, for example,…

Robotics · Computer Science 2025-10-13 Martin Schuck , Jan Brüdigam , Sandra Hirche , Angela Schoellig

Most data intensive applications often access only a few fields of the objects they are operating on. Since NVM provides fast, byte-addressable access to durable memory, it is possible to access various fields of an object stored in NVM…

Distributed, Parallel, and Cluster Computing · Computer Science 2018-07-18 Johnu George , Ramdoot Pydipaty , Xinyuan Huang , Amit Saha , Debo Dutta , Gary Wang , Uma Gangumalla

Both SRAM and DRAM have stopped scaling: there is no technical roadmap to reduce their cost (per byte/GB). As a result, memory now dominates system cost. This paper argues for a paradigm shift from today's simple memory hierarchy toward…

Neural language models are black-boxes--both linguistic patterns and factual knowledge are distributed across billions of opaque parameters. This entangled encoding makes it difficult to reliably inspect, verify, or update specific facts.…

Choosing the best memory layout for each hardware architecture is increasingly important as more and more programs become memory bound. For portable codes that run across heterogeneous hardware architectures, the choice of the memory layout…

Performance · Computer Science 2024-04-15 Bernhard Manfred Gruber

Neural word representations are at the core of many state-of-the-art natural language processing models. A widely used approach is to pre-train, store and look up word or character embedding matrices. While useful, such representations…

Computation and Language · Computer Science 2019-06-05 Chinnadhurai Sankar , Sujith Ravi , Zornitsa Kozareva