English
Related papers

Related papers: Understanding Memory Modules on Learning Simple Al…

200 papers

Large language models often expose their brittleness in reasoning tasks, especially while executing long chains of reasoning over context. We propose MemReasoner, a new and simple memory-augmented LLM architecture, in which the memory…

Computation and Language · Computer Science 2025-03-12 Payel Das , Ching-Yun Ko , Sihui Dai , Georgios Kollias , Subhajit Chaudhury , Aurelie Lozano

Multi-agent reinforcement learning (MARL) extends (single-agent) reinforcement learning (RL) by introducing additional agents and (potentially) partial observability of the environment. Consequently, algorithms for solving MARL problems…

Multiagent Systems · Computer Science 2019-09-12 Yilun Zhou , Derrik E. Asher , Nicholas R. Waytowich , Julie A. Shah

Mechanistic interpretability aims to understand how neural networks generalize beyond their training data by reverse-engineering their internal structures. We introduce patterning as the dual problem: given a desired form of generalization,…

Machine Learning · Computer Science 2026-01-21 George Wang , Daniel Murfet

The gradient boosting machine is one of the powerful tools for solving regression problems. In order to cope with its shortcomings, an approach for constructing ensembles of gradient boosting models is proposed. The main idea behind the…

Machine Learning · Computer Science 2020-10-14 Andrei V. Konstantinov , Lev V. Utkin

Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, sparsely activated memory layers complement compute-heavy dense feed-forward layers, providing dedicated…

Computation and Language · Computer Science 2024-12-23 Vincent-Pierre Berges , Barlas Oğuz , Daniel Haziza , Wen-tau Yih , Luke Zettlemoyer , Gargi Ghosh

Conditional computation and modular networks have been recently proposed for multitask learning and other problems as a way to decompose problem solving into multiple reusable computational blocks. We propose a new approach for learning…

Machine Learning · Computer Science 2021-07-26 Andrey Zhmoginov , Dina Bashkirova , Mark Sandler

Today, the dominant paradigm for training neural networks involves minimizing task loss on a large dataset. Using world knowledge to inform a model, and yet retain the ability to perform end-to-end training remains an open question. In this…

Machine Learning · Computer Science 2020-08-21 Tao Li , Vivek Srikumar

Neural networks leverage robust internal representations in order to generalise. Learning them is difficult, and often requires a large training set that covers the data distribution densely. We study a common setting where our task is not…

Universality is a key hypothesis in mechanistic interpretability -- that different models learn similar features and circuits when trained on similar tasks. In this work, we study the universality hypothesis by examining how small neural…

Machine Learning · Computer Science 2023-05-26 Bilal Chughtai , Lawrence Chan , Neel Nanda

Neural networks often learn simple explanations that fit the majority of the data while memorizing exceptions that deviate from these explanations.This behavior leads to poor generalization when the learned explanations rely on spurious…

Machine Learning · Computer Science 2024-12-11 Reza Bayat , Mohammad Pezeshki , Elvis Dohmatob , David Lopez-Paz , Pascal Vincent

Policy learning for partially observed control tasks requires policies that can remember salient information from past observations. In this paper, we present a method for learning policies with internal memory for high-dimensional,…

Machine Learning · Computer Science 2015-09-24 Marvin Zhang , Zoe McCarthy , Chelsea Finn , Sergey Levine , Pieter Abbeel

Tasks in which rewards depend upon past information not available in the current observation set can only be solved by agents that are equipped with short-term memory. Usual choices for memory modules include trainable recurrent hidden…

Machine Learning · Computer Science 2024-12-18 Kevin McKee

We study class-incremental learning, a training setup in which new classes of data are observed over time for the model to learn from. Despite the straightforward problem formulation, the naive application of classification models to…

Computer Vision and Pattern Recognition · Computer Science 2022-10-11 Ahmet Iscen , Thomas Bird , Mathilde Caron , Alireza Fathi , Cordelia Schmid

Feed-forward neural networks consist of a sequence of layers, in which each layer performs some processing on the information from the previous layer. A downside to this approach is that each layer (or module, as multiple modules can…

Machine Learning · Computer Science 2020-10-19 Alex Lamb , Anirudh Goyal , Agnieszka Słowik , Michael Mozer , Philippe Beaudoin , Yoshua Bengio

We augment recurrent neural networks with an external memory mechanism that builds upon recent progress in metalearning. We conceptualize this memory as a rapidly adaptable function that we parameterize as a deep neural network. Reading…

Neural and Evolutionary Computing · Computer Science 2019-12-04 Tsendsuren Munkhdalai , Alessandro Sordoni , Tong Wang , Adam Trischler

Learning models that execute algorithms can enable us to address a key problem in deep learning: generalizing to out-of-distribution data. However, neural networks are currently unable to execute recursive algorithms because they do not…

Machine Learning · Computer Science 2023-11-22 Jonas Jürß , Dulhan Jayalath , Petar Veličković

Modern large language models (LLMs) excel at tasks that require storing and retrieving knowledge, such as factual recall and question answering. Transformers are central to this capability because they can encode information during training…

Machine Learning · Statistics 2026-03-18 Nuri Mert Vural , Alberto Bietti , Mahdi Soltanolkotabi , Denny Wu

Multiple Kernel Learning is a conventional way to learn the kernel function in kernel-based methods. MKL algorithms enhance the performance of kernel methods. However, these methods have a lower complexity compared to deep learning models…

Machine Learning · Computer Science 2023-05-05 Ahmad Navid Ghanizadeh , Kamaledin Ghiasi-Shirazi , Reza Monsefi , Mohammadreza Qaraei

Despite advances in deep learning, neural networks can only learn multiple tasks when trained on them jointly. When tasks arrive sequentially, they lose performance on previously learnt tasks. This phenomenon called catastrophic forgetting…

Machine Learning · Computer Science 2018-05-29 Nitin Kamra , Umang Gupta , Yan Liu

This tutorial introduces a new and powerful set of techniques variously called "neural machine translation" or "neural sequence-to-sequence models". These techniques have been used in a number of tasks regarding the handling of human…

Computation and Language · Computer Science 2017-03-07 Graham Neubig