28 papers · ranked by Valyu relevance
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…
Ahmed Mehedi Nizam, Zeheng Wang
We introduce a supervised learning method that classifies each test point by selecting the class for which its inclusion causes minimum displacement of the class’s existing n-th central moment. After each such inclusion, the n-th central moment of the corresponding class is updated by some incremental calculations in…
Jason D. Hartline
A fundamental challenge for modern economics is to understand what happens when actors in an economy are replaced with algorithms. Like rationality has enabled understanding of outcomes of classical economic actors, no-regret can enable the understanding of outcomes of algorithmic actors. This review article covers the…
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…
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…
Pranav Mahajan, Ben Seymour
The seminal reward prediction error theory of dopamine function faces several key challenges. Most notable is the difficulty learning multiple rewards simultaneously, inefficient on-policy learning, and accounting for heterogeneous striatal responses in the tail of the striatum. We propose a normative framework, based…
Fengjiao Jia, Hengkai Wang, Deyu Shen, Dandan Sang + 5 more
Carbon dots (CDs) have emerged as frontier materials in multidisciplinary research owing to their unique optical properties and physicochemical characteristics. However, issues such as the reliance on trial-and-error experimentation for synthetic preparation and the difficulty in systematically revealing…
Ezekiel Williams, Alexandre Payeur, Guillaume Lajoie
Biological and neuromorphic recurrent neural networks (RNNs) are subject to spatial and temporal locality constraints on the information that can plausibly be used during learning. A common strategy to satisfy these constraints is to modify gradient descent by neglecting non-local terms to varying degrees, as in random…
Authors not listed
Terminally labeled DNA oligonucleotides have wide applications in modern biology and biotechnological applications. It has been observed that the fluorescent intensity of light released from these fluorescent labels is heavily influenced by the terminal sequence of nucleotides. Recent studies have assayed and published…
Rocco A. Servedio
Leslie Valiant's 1984 paper "A Theory of the Learnable" [[Val84]], reproduced in this volume, has the unusual distinction of having changed the course of several scientific disciplines. Within theoretical computer science it was one of the key works giving rise to the field now known as computational learning theory…
Roman Kononov, Nikita Pospelov, K. V. Anokhin, Vladimir I. Nekorkin + 1 more
Understanding how learning algorithms shape the computational strategies that emerge in neural networks remains a fundamental challenge in machine intelligence. While network architectures receive extensive attention, the role of the learning paradigm itself in determining emergent dynamics remains largely unexplored.…
Muhammad Muneeb, David B. Ascher, YooChan Myung
Identifying disease-associated genes enables the development of precision medicine and the understanding of biological processes. Genome-wide association studies (GWAS), gene expression data, biological pathway analysis, and protein network analysis are among the techniques used to identify causal genes. We propose a…
Yan Feng, Changdong Chen
Alzheimer’s disease (AD) is the most common cause of dementia, affecting 55 million people worldwide. Its characteristics include the accumulation of senile plaques and neurofibrillary tangles. This disease is associated with changes in the concentration of AD biomarkers, such as microRNAs, amyloid peptides, Tau…
Pranav Mahajan, Ben Seymour
The seminal reward prediction error account of dopamine has been highly successful, but faces several key challenges. Most notable are the difficulty of learning multiple rewards simultaneously, inefficient on-policy learning, and accounting for the heterogeneous striatal responses observed across and within striatal…
Mert Yuksekgonul, D. M. Koceja, Xinhao Li, Federico Bianchi + 7 more
How can we use AI to discover a new state of the art for a scientific problem? Prior work in test-time scaling, such as AlphaEvolve, performs search by prompting a frozen LLM. We perform reinforcement learning at test time, so the LLM can continue to train, but now with experience specific to the test problem. This…
Authors not listed
The integration of machine learning methods is transforming many areas of research by, for instance, accelerating molecular dynamics simulations and enabling improved prediction and optimization of chemical reactions. However, despite this progress, the adoption of data-driven approaches in atomic layer deposition…
Jan Arne Telle, Brigt Håvardstun, Jose Hernandez-Orallo
Most models of machine teaching and learning assume the learner makes no errors in its internal deductive inference. However, humans and large language models in few-shot learning regimes are two important examples of learners where this does not hold. They fail on some consistency checks, and they can fail…
Russell Jeter, Dmitrii Todorov, Yaroslav Molkov
A clinician guiding a stroke patient through a 45-minute rehabilitation session, a coach planning a training day, a teacher choosing the order of practice problems, they all face the same question: “given everything practiced so far, what should the next trial be?” The motor-learning literature offers two coarse…
Stephen B Lee, Alexis B Carter, Muhammad Hamis Haider, Seok-Bum Ko + 2 more
Artificial intelligence (AI) is already fundamentally changing society, with medicine being no exception. AI will impact how we practice, how hospitals operate, and even the practice of medicine itself. The use of AI-based products has already begun, with examples including AI scribes and large language models such as…
Seouh-won Yi, Min-hwan Oh
We propose feature perturbation, a simple yet effective exploration strategy for contextual bandits that injects randomness directly into feature inputs, instead of randomizing unknown parameters or adding noise to rewards. Remarkably, this algorithm achieves O e( d √ T) worst-case regret bound for generalized linear…
Manu Srinath Halvagal, Sebastian Lee, SueYeon Chung
Reinforcement Learning (RL) has long served as a model for goal-directed animal behavior in neuroscience. Modern deep RL has shown remarkable success across many domains, further strengthening this connection. The ability to learn abstract representations of high-dimensional state spaces underlies much of this success.…
Authors not listed
Realizing the promise of artificial intelligence (AI) to accelerate scientific progress and deliver technological impact depends on how effectively AI can be integrated into real-world decision- making processes. As Peter Norvig states, “Somewhat remarkably, almost all AI research until very recently has assumed that…
Authors not listed
Computational chemistry has entered a new era where machine learning (ML) models—particularly graph neural networks and machine learning force fields—routinely deliver quantum mechanical accuracy at classical speeds, scaling to millions of atoms and reshaping workflows in drug discovery, catalysis, and materials…
Mingbin Tang, Yejun Zheng, Lianbao Li, Li Cao + 2 more
Complex engineering optimization problems often exhibit high-dimensional, multi-constraint, and nonlinear characteristics. Traditional deterministic optimization methods rely on gradient information and have limited optimization ranges, making it difficult to meet the requirements of efficient and accurate solutions.…
Charlotte Collingwood, Francesca Greenstreet, Marcus Stephenson-Jones, Rafal Bogacz
Action-selection is determined by a combination of goal-directed and habitual processes. Habits are defined as the reward-independent, stimulus-response relationships which form when an action is regularly executed in the same context, regardless of outcome. An influential computational model proposes that habit…
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…
Zhaolin Lu, Jiayuan Guo, Tian Yuan, Yue Zhang + 8 more
Artificial intelligence is rapidly entering higher education, yet many students experience anxiety when learning to use it. This study examines how performance expectations, perceived explainability, and perceived ethical risks shape two algorithm attitudes, algorithm aversion and algorithm appreciation, and how these…
Authors not listed
The Hidden Subgroup Problem (HSP) unifies several landmark quantum algorithms, yet systematic exploration of its variants and modern applications has slowed. This paper revives HSP-based algorithm design by examining new group structures with direct relevance to post-quantum cryptography, lattice problems, and…