27 papers · ranked by Valyu relevance
Yefeng Liu, Jingjing Liu, Yanwei Ma, Shuai Wang + 2 more
A key part of CNC machine tools is the rolling bearing, and thus, it is vital to employ a data-driven approach for fault diagnosis. This paper proposes a two-stage fusion sparse learning algorithm for fault data processing that can identify and diagnose the fault types of rolling bearings based on sensor measurement…
Dhruva V. Raman, Christopher R. Dunne, Katie Davyson, Timothy O’Leary
Animals inhabit continually changing environments where it is not always possible to infer causes of relevant changes, such as the appearance of a new threat. In such nonstationary settings, learning a predictive model is challenging because a surprising observation could be due to chance, or due to systematic but…
Nathan Boyer, Dorian Baudry, Patrick Rebeschini
We study the problem of linear contextual bandits with paid observations, where at each round the learner selects an action in order to minimize its loss in a given context, and can then decide to pay a fixed cost to observe the loss of any arm. Building on the Followthe-Regularized-Leader framework with efficient…
Armin Bazarjani, Payam Piray
Cognitive maps enable flexible behavior by providing reusable internal representations of task structure. The successor representation, a predictive map that encodes expected future state occupancy, has been proposed as one way such maps might be computed in the brain, but its policy dependence severely limits flexible…
Riccardo Molteni, Casper Gyurik, Vedran Dunjko
Quantum computers are believed to bring computational advantages in simulating quantum many-body systems. However, recent works have shown that classical machine learning algorithms are able to predict numerous properties of quantum systems with classical data. Despite examples of learning tasks with provable quantum…
Nicolas Diekmann, Silke Lissek, Metin Üngör, Sen Cheng
The progress of learning is usually quantified by averaging responses across participants and/or multiple trials within a block. However, such approaches obscure the trial-by-trial progress of learning, which has been shown recently to express a rich variety of dynamics. An alternative approach which does not suffer…
Kareem Amin, Alex Bie, Weiwei Kong, Umar Syed + 1 more
The prevalence and low cost of LLMs have led to a rise of synthetic content. From review sites to court documents, "natural" content has been contaminated by data points that appear similar to natural data, but are in fact LLM-generated. In this work we revisit fundamental learning theory questions in this, now…
Adam R. Klivans, Shyamal Patel, Konstantinos Stavropoulos, Arsen Vasilyan
Recent work on provably efficient algorithms for learning with distribution shift has focused on two models: PQ learning (Goldwasser et al. (2020)) and TDS learning (Klivans et al. (2024)). Algorithms for TDS learning are allowed to reject a test set entirely if distribution shift is detected. In contrast, PQ learners…
Emma Brunskill, Ishani Karmarkar, Zhaoqi Li
A key goal in stochastic contextual linear bandits is to efficiently learn a near-optimal policy. Prior algorithms for this problem learn a policy by strategically sampling actions but naively (passively) sampling contexts from the underlying context distribution. However, in many practical scenarios -- including…
Bo Xue, Ji Cheng, Haodong Jing, Hongzong Li + 1 more
This paper studies generalized low-rank matrix bandits with multiple prioritized objectives. At each round, the learner selects a matrix-valued arm and observes a vector-valued reward, whose components correspond to multiple objectives with different priority levels. Each objective is governed by an objective-specific…
Authors not listed
Collective variables (CVs) are essential for interpreting and accelerating rare events in molecular simulations. However, their design remains limited by the requirement of differentiability with respect to atomic coordinates. This constraint excludes many powerful structural descriptors that are routinely used for…
Yang Cao, Bingchuan Wu, Miao Wen, Yang Lou
Differential evolution has become one of the mainstream solvers for complex optimization problems due to its concise structure and strong global search ability. However, the performance of the DE algorithm is highly sensitive to its mutation and crossover strategies and related control parameters. Traditional adaptive…
Yukun Yang, Wolfgang Maass
Most current methods for goal-directed action selection in the face of changing goals and contingencies require DNNs or LLMs. Therefore they are less suited for implementation in edge devices, where low energy-consumption is imperative. The brain shows that similar functionality can be produced with just 20W, even with…
Authors not listed
Phase equilibrium calculations are crucial in chemical engineering design and optimization processes. The PC-SAFT equation of state (EoS) can precisely calculate phase equilibrium, but is relatively complex and computationally intensive. Surrogate models are mathematically simple models that map or regress the…
Hagar F. Gouda, Fatma D. M. Abdallah
Ensemble machine learning (ML) algorithms, such as bagging and boosting, are powerful decision-support tools that enhance disease prediction and risk management in the veterinary field. Lumpy Skin Disease (LSD) poses a significant threat to livestock health and results in substantial economic losses. This study aims to…
Steven A. Frank, Antonio M. Scarfone
Diverse learning algorithms, optimization methods, and natural selection share a common mathematical structure despite their apparent differences. Here, I show that a simple notational partitioning of change by the Price equation reveals a universal force-metric-bias (FMB) law: $Δθ=(Mf+b+ξ)$. The force $f$ drives…
Naoki Awaya, Li Ma
We propose an unsupervised tree boosting algorithm for inferring the underlying sampling distribution of an i.i.d. sample based on fitting additive tree ensembles in a manner analogous to supervised tree boosting. Integral to the algorithm is a new notion of “addition” on probability distributions that leads to a…
Authors not listed
Transition state (TS) geometries of chemical reactions are key to understanding reaction mechanisms and estimating kinetic properties. Inferring these directly from 2D reaction graphs offers chemists a powerful tool for rapid and accessible reaction analysis. Quantum chemical methods for computing TSs are…
Authors not listed
Quantitative Structure Activity Relationship (QSAR) remains an effective tool for early-stage chemical modelling and virtual screening in drug design. The advancements in this field are led by two core paradigms, 1) descriptor engineering, where complex fixed-length vectors of compounds are generated and conventional…
Niall Donnelly, Edward Keedwell, John Parkinson, Andy J. Wills
As artificial intelligence systems continue to overcome evermore challenging tasks, researchers have suggested that the time is ripe to begin evaluating these systems along more psychologically inspired lines. This study seeks to build upon these recommendations by evaluating two machine learning models, A-Learning and…
Authors not listed
Machine olfaction—the artificial replication of the sense of smell—faces significant challenges due to the absence of large, standardized training datasets. Unlike vision, language, and audio models, which benefit from extensive corpora such as ImageNet, GLUE, and AudioSet, olfaction lacks scaled equivalents and…
Nouhaila Houssa, Seddik Abdelalim, Ilias Elmouki
This study addresses the practical problem of building reliable and interpretable tools to support the early detection of breast and prostate cancers. We investigate how the choice of numerical optimization method affects the training of logistic regression (LR) models for binary cancer classification. In particular…
Jianning Chen, Masakazu Taira, Kenji Doya
Behavioral strategies can change in response to environmental and internal states, either gradually or abruptly, enabling flexible adaptation. Such strategy regulation is central to meta-learning, the ability to learn to learn. Previous studies analyzed temporal or condition-dependent strategy change using models and…
Mingchen Ma, Guyang Cao, Jelena Diakonikolas, Ilias Diakonikolas
We study the problem of learning a drifting concept in the presence of Massart noise. In this framework, an online learner has access to a history of independent samples whose labels are noisy versions of a target concept that may change from round to round. The goal is to output, in each round, a hypothesis with small…
Gammerman, Alexander
This Inaugural Lecture was given at Royal Holloway University of London in 1996. It covers an introduction to machine learning and describes various theoretical advances and practical projects in the field. The Lecture here is presented in its original format, but a few remarks have been added in 2025 to reflect recent…
Michael L. Helde, Alexander G. Dimitrov
We adapted an olfactory neuromorphic algorithm to image and sound recognition. To achieve this, we carried out specific preprocessing procedures that were tailored to each modality. For images, we used the NIST digits dataset directly. For sound, we used samples from the Google Speech Command dataset. A gammatone…
Authors not listed
The automated discovery of chemical and catalytic reactions remains a major challenge in computational chemistry, particularly in complex systems where conventional methods struggle to identify optimal searching directions. Here, we propose Loxodynamics, a machine-learning-driven approach for reaction exploration via…