中文
相关论文

相关论文: Keeping it simple: Implementation and performance …

200 篇论文

In this document we shows a first implementation and some preliminary results of a new theory, facing Machine Learning problems in the frameworks of Classical Mechanics and Variational Calculus. We give a general formulation of the problem…

机器学习 · 计算机科学 2017-01-11 Marco Gori , Marco Maggini , Alessandro Rossi

How do neural language models acquire a language's structure when trained for next-token prediction? We address this question by deriving theoretical scaling laws for neural network performance on synthetic datasets generated by the Random…

机器学习 · 计算机科学 2025-05-13 Francesco Cagnetta , Alessandro Favero , Antonio Sclocchi , Matthieu Wyart

In lifelong learning, data are used to improve performance not only on the present task, but also on past and future (unencountered) tasks. While typical transfer learning algorithms can improve performance on future tasks, their…

Active learning aims to select a small subset of data for annotation such that a classifier learned on the data is highly accurate. This is usually done using heuristic selection methods, however the effectiveness of such methods is limited…

计算与语言 · 计算机科学 2017-08-09 Meng Fang , Yuan Li , Trevor Cohn

Vibrational resonance focuses on the resonance behavior of a nonlinear system when it is subjected to both a weak low-frequency characteristic signal and a high-frequency auxiliary signal. A traditional Duffing system has a fixed natural…

适应与自组织系统 · 物理学 2026-01-13 Zhongqiu Wan , Jianhua Yang , Feng Tian , Huatao Chen , Miguel A. F. Sanjuán

Inspired by the \emph{Well-initialized Lottery Ticket Hypothesis (WLTH)}, we introduce Soft-Transformer (Soft-TF), a parameter-efficient framework for continual learning that leverages soft, real-valued subnetworks over a frozen pre-trained…

机器学习 · 计算机科学 2026-04-29 Haeyong Kang , Chang D. Yoo

Although deep reinforcement learning has recently been very successful at learning complex behaviors, it requires a tremendous amount of data to learn a task. One of the fundamental reasons causing this limitation lies in the nature of the…

机器人学 · 计算机科学 2022-09-19 Zhenshan Bing , Alexander Koch , Xiangtong Yao , Kai Huang , Alois Knoll

Co-adaptation is a special form of on-line learning where an algorithm $\mathcal{A}$ must assist an unknown algorithm $\mathcal{B}$ to perform some task. This is a general framework and has applications in recommendation systems, search,…

机器学习 · 统计学 2016-12-01 Michael Rabadi

Neural network-based systems can now learn to locate the referents of words and phrases in images, answer questions about visual scenes, and execute symbolic instructions as first-person actors in partially-observable worlds. To achieve…

计算与语言 · 计算机科学 2019-10-02 Felix Hill , Stephen Clark , Karl Moritz Hermann , Phil Blunsom

Meta-learning, the notion of learning to learn, enables learning systems to quickly and flexibly solve new tasks. This usually involves defining a set of outer-loop meta-parameters that are then used to update a set of inner-loop…

机器学习 · 计算机科学 2023-03-17 Chris Lu , Sebastian Towers , Jakob Foerster

We consider active learning with logged data, where labeled examples are drawn conditioned on a predetermined logging policy, and the goal is to learn a classifier on the entire population, not just conditioned on the logging policy. Prior…

机器学习 · 计算机科学 2018-06-14 Songbai Yan , Kamalika Chaudhuri , Tara Javidi

Behavioral skills or policies for autonomous agents are conventionally learned from reward functions, via reinforcement learning, or from demonstrations, via imitation learning. However, both modes of task specification have their…

Humans can infer a great deal about the meaning of a word, using the syntax and semantics of surrounding words even if it is their first time reading or hearing it. We can also generalise the learned concept of the word to new tasks.…

计算与语言 · 计算机科学 2020-07-21 Talip Ucar , Adrian Gonzalez-Martin , Matthew Lee , Adrian Daniel Szwarc

Large-scale pretrained language models are the major driving force behind recent improvements in performance on the Winograd Schema Challenge, a widely employed test of common sense reasoning ability. We show, however, with a new diagnostic…

计算与语言 · 计算机科学 2020-05-08 Mostafa Abdou , Vinit Ravishankar , Maria Barrett , Yonatan Belinkov , Desmond Elliott , Anders Søgaard

Adaptive filtering algorithms are pervasive throughout signal processing and have had a material impact on a wide variety of domains including audio processing, telecommunications, biomedical sensing, astrophysics and cosmology, seismology,…

声音 · 计算机科学 2022-11-23 Jonah Casebeer , Nicholas J. Bryan , Paris Smaragdis

In the present paper we show that distributional information is particularly important when considering concept availability under implicit language learning conditions. Based on results from different behavioural experiments we argue that…

计算与语言 · 计算机科学 2016-06-30 Dimitrios Alikaniotis , John N. Williams

Pretraining on large, semantically rich datasets is key for developing language models. Surprisingly, recent studies have shown that even synthetic data, generated procedurally through simple semantic-free algorithms, can yield some of the…

机器学习 · 计算机科学 2025-05-29 Zachary Shinnick , Liangze Jiang , Hemanth Saratchandran , Anton van den Hengel , Damien Teney

Increased adaptability of RNN language models leads to improved predictions that benefit many applications. However, current methods do not take full advantage of the RNN structure. We show that the most widely-used approach to adaptation…

计算与语言 · 计算机科学 2017-04-24 Aaron Jaech , Mari Ostendorf

Many Natural Language Processing applications nowadays rely on pre-trained word representations estimated from large text corpora such as news collections, Wikipedia and Web Crawl. In this paper, we show how to train high-quality word…

计算与语言 · 计算机科学 2017-12-29 Tomas Mikolov , Edouard Grave , Piotr Bojanowski , Christian Puhrsch , Armand Joulin

A long-standing goal in robotics is to build robots that can perform a wide range of daily tasks from perceptions obtained with their onboard sensors and specified only via natural language. While recently substantial advances have been…

机器人学 · 计算机科学 2022-08-31 Oier Mees , Lukas Hermann , Wolfram Burgard