27 papers · ranked by Valyu relevance
Daniel A. Braun, Carsten Mehring, Daniel M. Wolpert
‘Learning to learn’ phenomena have been widely investigated in cognition, perception and more recently also in action. During concept learning tasks, for example, it has been suggested that characteristic features are abstracted from a set of examples with the consequence that learning of similar tasks is facilitated-a…
Daniel A. Braun, Stephan Waldert, Ad Aertsen, Daniel M. Wolpert + 2 more
'Carsten Mehring' 'Paul L. Gribble'] Learning is often understood as an organism's gradual acquisition of the association between a given sensory stimulus and the correct motor response. Mathematically, this corresponds to regressing a mapping between the set of observations and the set of actions. Recently, however…
Christoffer Lundbak Olesen, Nace Mikuš, Mads Hansen, Nicolas Legrand + 3 more
Biological cognition depends on learning-structured representations in ambiguous environments. Computational models of structure learning typically frame this as an inference problem, but often overlook the temporally extended dynamics that shape learning trajectories under ambiguity. In this paper, we reframe…
Benjamin Lansdell, Konrad P. Körding
In good old-fashioned artificial intelligence (GOFAI), humans specified systems that solved problems. Much of the recent progress in AI has come from replacing human insights by learning. However, learning itself is still usually built by humans – specifically the choice that parameter updates should follow the…
Gustav Šourek, Martin Svatoš, Filip Železný, Steven Schockaert + 1 more
'Ondřej Kuželka'] Lifted Relational Neural Networks (LRNNs) describe relational domains using weighted firstorder rules which act as templates for constructing feed-forward neural networks. While previous work has shown that using LRNNs can lead to state-of-the-art results in various ILP tasks, these results depended…
Niloufar Razmi, Xufeng Caesar Dai, Leah Bakst, Matthew R. Nassar
People rapidly recalibrate their expectations about the world in the face of surprising observations. This recalibration should depend on the temporal structure of the environment, however how people should and do learn temporal structures remains unknown. To examine this gap, we developed a Bayesian model that infers…
Andrea E. Martin, Leonidas A. A. Doumas
Humans learn complex latent structures from their environments (e.g., natural language, mathematics, music, social hierarchies). In cognitive science and cognitive neuroscience, models that infer higher-order structures from sensory or first-order representations have been proposed to account for the complexity and…
James L. McClelland, Bruce L. McNaughton, Andrew K. Lampinen
According to complementary learning systems theory, integrating new memories into the neocortex of the brain without interfering with what is already known depends on a gradual learning process, interleaving new items with previously learned items. However, empirical studies show that information consistent with prior…
Daniel L. Kimmel, Kimberly L. Stachenfeld, Nikolaus Kriegeskorte, Stefano Fusi + 2 more
Abstraction and generalization are essential for flexible decision-making in novel situations. Recent work in humans and monkeys has shown how abstract variables are encoded by the representational geometry of neural population activity. However, these observations—which are typically made after learning has…
Anna Székely, Balázs Török, Mariann Kiss, Karolina Janacsek + 2 more
'Dezső Németh' 'Gergő Orbán'] Title: Abstract Transfer learning, the reuse of newly acquired knowledge under novel circumstances, is a critical hallmark of human intelligence that has frequently been pitted against the capacities of artificial learning agents. Yet, the computations relevant to transfer learning have…
Xiangjuan Ren, Muzhi Wang, Tingting Qin, Fang Fang + 2 more
Humans naturally seek knowledge, yet integrating vast, fragmented information remains challenging. Traditionally, knowledge acquisition has relied on random walks within network—an unguided and inefficient process. We introduce compressive learning, a framework that embeds higher-order structural features—specifically…
James C. R. Whittington, Timothy Müller, Shirley Mark, Caswell Barry + 1 more
'Timothy E.J. Behrens'] A central problem to understanding intelligence is the concept of generalisation. This allows previously learnt structure to be exploited to solve tasks in novel situations differing in their particularities. We take inspiration from neuroscience, specifically the hippocampal-entorhinal system…
Alon B Baram, Timothy H Muller, Hamed Nili, Mona Garvert + 1 more
Knowledge of the structure of a problem, such as relationships between stimuli, enables rapid learning and flexible inference. Humans and other animals can abstract this structural knowledge and generalise it to solve new problems. For example, in spatial reasoning, shortest-path inferences are immediate in new…
Tagir Akhmetshin, Arkadii Lin, Timur Madzhidov, Alexandre Varnek
Autoencoders represent a promising technique for the inverse quantitative structure-activity relationship (QSAR) task. However, undesirable bias, such as atom ordering, affects the neighbourhood behaviour of autoencoders’ latent space and, consequently, usage of the latent vectors as variables in machine-learning…
Timo Flesch, Andrew Saxe, Christopher Summerfield
Title: Highlights 1. Both natural and artificial agents face the challenge of learning in ways that support effective future behaviour. 2. This may be achieved by different learning regimes, associated with distinct dynamics, and differing dimensionality and geometry of neural task representations. 3. Where two…
Adam Marblestone, Greg Wayne, Konrad P. Körding
Neuroscience has focused on the detailed implementation of computation, studying neural codes, dynamics and circuits. In machine learning, however, artificial neural networks tend to eschew precisely designed codes, dynamics or circuits in favor of brute force optimization of a cost function, often using simple and…
Jacob Russin, Ellie Pavlick, Michael J. Frank
Human learning embodies a striking duality: sometimes, we appear capable of following logical, compositional rules and benefit from structured curricula (e.g., in formal education), while other times, we rely on an incremental approach or trial-and-error, learning better from curricula that are randomly interleaved.…
Sreejan Kumar, Ishita Dasgupta, Jonathan D. Cohen, Nathaniel D. Daw + 1 more
'Thomas L. Griffiths'] In recent years, meta-learning, in which a model is trained on a family of tasks (i.e. a task distribution), has emerged as an approach to training neural networks to perform tasks that were previously assumed to require structured representations, making strides toward closing the gap between…
Kamil Rocki
There exists a theory of a single general-purpose learning algorithm which could explain the principles its operation. It assumes the initial rough architecture, a small library of simple innate circuits which are prewired at birth. and proposes that all significant mental algorithms are learned. Given current…
Authors not listed
Predicting protein-ligand binding affinity from three-dimensional (3D) structural data is a central task in structure-based drug discovery, yet it remains challenging due to limited data availability, structural complexity, and the sparse nature of 3D molecular representations. In this study, we investigate the…
N. Menghi, S. Vigano’, W. J. Johnston, S. Elnagar + 2 more
Learning depends not only on the content of what we learn, but also on how we learn and on how experiences are structured over time. To investigate how task similarity and training regime interact during learning, we trained participants on spatial and conceptual learning tasks that shared either similar or distinct…
Anthony Onwuli, Keith T. Butler, Aron Walsh
High-dimensional representations of the elements have become common within the field of materials informatics to build useful, structure-agnostic models for the chemistry of materials. However, the characteristics of elements change when they adopt a given oxidation state, with distinct structural preferences and…
James M. Foster, Matt Jones
Research in analogical reasoning suggests that higher-order cognitive functions such as abstract reasoning, far transfer, and creativity are founded on recognizing structural similarities among relational systems. Here we integrate theories of analogy with the computational framework of reinforcement learning (RL). We…
Derek van Tilborg, Francesca Grisoni
Deep learning is accelerating drug discovery. However, current approaches are often affected by limitations in the available data, e.g., in terms of size or molecular diversity. Active deep learning has an untapped potential for low-data drug discovery, as it allows to improve a model iteratively during the screening…
Alexandra R. van den Berg, Pieter R. Roelfsema, Sander M. Bohte, Shenbing Kuang
'Shenbing Kuang'] The acquisition of knowledge and skills does not occur in isolation but learning experiences amalgamate within and across domains. The process through which learning can accelerate over time is referred to as learning-to-learn or meta-learning. While meta-learning can be implemented in recurrent…
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…
Paul Francoeur, Daniel Penaherrera, David Koes
The immense size of chemical space, the relative scarcity of high quality data, and the cost of running experiments to accurately measure molecular properties makes active learning (AL) an attractive approach to efficiently explore the space and train high-quality models for molecular property prediction. While AL is…