24 papers · ranked by Valyu relevance
Jessica Passlack, Andrew F MacAskill
The ability to use the context we are in to flexibly adjust our decision-making is vital for navigating a complex world. To do this, the brain must i) use environmental features and behavioural outcomes to distinguish between different, often hidden contexts; and ii) learn how to use these inferred contexts to guide…
Jessica Passlack, Andrew F. MacAskill, Alejandro Tabas
The ability to use context to flexibly adjust our decision-making is vital for navigating a complex world. To do this, the brain must both use environmental features and behavioural outcomes to distinguish between different, often hidden contexts; and also learn how to use these inferred contexts to guide behaviour.…
Fleming C. Peck, Hongjing Lu, Jesse Rissman
Humans readily extract statistical regularities from experience, yet natural environments require flexible adaptation when associative structures shift across changing contexts, often without warning. Across two experiments, we show that humans can incidentally learn overlapping and conflicting visual associations even…
Thomas Walther, Nicolas Diekmann, Sandhiya Vijayabaskaran, José R. Donoso + 3 more
'José R. Donoso' 'Denise Manahan-Vaughan' 'Laurenz Wiskott' 'Sen Cheng'] The context-dependence of extinction learning has been well studied and requires the hippocampus. However, the underlying neural mechanisms are still poorly understood. Using memory-driven reinforcement learning and deep neural networks, we…
William D. Marks, Jun Yokose, Takashi Kitamura, Sachie K. Ogawa
Contextual learning is a critical component of episodic memory and important for living in any environment. Context can be described as the attributes of a location that are not the location itself. This includes a variety of non-spatial information that can be derived from sensory systems (sounds, smells, lighting…
Martina Zellin, Markus Conci, Adrian von Mühlenen, Hermann J. Müller + 1 more
'Elkan Akyürek'] Visual search for a target object can be facilitated by the repeated presentation of an invariant configuration of nontargets (‘contextual cueing’). Here, we tested adaptation of learned contextual associations after a sudden, but permanent, relocation of the target. After an initial learning phase…
Vasilis Syrgkanis, Akshay Krishnamurthy, Robert E. Schapire
We provide the first oracle efficient sublinear regret algorithms for adversarial versions of the contextual bandit problem. In this problem, the learner repeatedly makes an action on the basis of a context and receives reward for the chosen action, with the goal of achieving reward competitive with a large class of…
Pascal Klink, Hany Abdulsamad, Boris Belousov, Jan Peters
Generalization and adaptation of learned skills to novel situations is a core requirement for intelligent autonomous robots. Although contextual reinforcement learning provides a principled framework for learning and generalization of behaviors across related tasks, it generally relies on uninformed sampling of…
Xiaoyu Chen, Shuliang Bai, Qidan Ren, Yi Chen + 3 more
'Ying Jiang' 'David Sewell'] Background Contextual cueing refers to the phenomenon in which individuals utilize frequently encountered environmental contexts, comprised of distractors, as cues to expedite a target search. Due to the conflict between the widespread occurrence of contextual cue transfer and the observed…
Gili Lior, Yuval Shalev, Gabriel Stanovsky, Ariel Goldstein
The human brain is an adaptive learning system that can generalize to new tasks and unfamiliar environments. The traditional view is that such adaptive behavior requires a structural change of the learning system (e.g., via neural plasticity). In this work, we use artificial neural networks, specifically large language…
Santiago Balseiro, Negin Golrezaei, Mohammad Mahdian, Vahab Mirrokni + 1 more
'Jon Schneider'] Authors are encouraged to submit new papers to INFORMS journals by means of a style file template, which includes the journal title. However, use of a template does not certify that the paper has been accepted for publication in the named journal. INFORMS journal templates are for the exclusive purpose…
Anna Heuser, Thomas Kesselheim
Motivated by stochastic optimization, we introduce the problem of learning from samples of contextual value distributions. A contextual value distribution can be understood as a family of real-valued distributions, where each sample consists of a context x and a random variable drawn from the corresponding real-valued…
Amr Sharaf, Hal Daumé
We describe MELˆ EE´ , a meta-learning algorithm for learning a good exploration policy in the interactive contextual bandit setting. Here, an algorithm must take actions based on contexts, and learn based only on a reward signal from the action taken, thereby generating an exploration/exploitation trade-off. MELˆ EE´…
Aniket Anand Deshmukh, Ürün Doǧan, Clayton Scott
Contextual bandits are a form of multi-armed bandit in which the agent has access to predictive side information (known as the context) for each arm at each time step, and have been used to model personalized news recommendation, ad placement, and other applications. In this work, we propose a multi-task learning…
Hua-Dong Xiong, Li Ji-An, Robert C. Wilson, Marcelo G. Mattar
A hallmark of intelligence is the ability to adapt behavior to changing environments, which requires adapting one’s own learning strategies. This phenomenon is known as learning to learn in cognitive science and meta-learning in artificial intelligence. While this phenomenon is well-established in humans and animals…
Marco Bertolini, Linlin Zhao, Djork-Arné Clevert, Floriane Montanari
The field of explainable AI applied to molecular property prediction models has often been reduced to deriving atomic contributions. This has impaired the interpretability of such models, as chemists rather think in terms of larger, chemically meaningful structures, which often do not simply reduce to the sum of their…
Hua-Dong Xiong, Li Ji-An, Robert C. Wilson, Marcelo G. Mattar
A hallmark of intelligence is the ability to adapt behavior to changing environments, which requires adapting one’s own learning strategies. This phenomenon is known as learning to learn or meta-learning. Although well established in humans and animals, a computational framework that characterizes how biological agents…
Authors not listed
Large Language Models (LLMs) based on transformer architectures excel at internet-scale tasks. However, real-world scientific scenarios—such as synthetic chemistry laboratories and autonomous experimental setups—typically involve incremental data generation in batches as new chemical reactions are conducted, unlike…
Derek van Tilborg, Helena Brinkmann, Emanuele Criscuolo, Luke Rossen + 2 more
Deep learning is becoming increasingly relevant in drug discovery, from de novo design to protein structure prediction and synthesis planning. However, it is often challenged by the small data regimes typical of certain drug discovery tasks. In such scenarios, deep learning approaches – which are notoriously…
Antonino Greco, Clara Rastelli, Leonardo Bonetti, Christoph Braun + 1 more
A longstanding question in cognitive science is whether the human brain learns sensory regularities that are irrelevant to ongoing behavior, a phenomenon known as incidental associative learning. Here, we provide evidence at the single subject level that humans indeed acquired such incidental associations and reveal…
Authors not listed
Early prediction of drug-induced organ toxicity remains a major bottleneck in drug discovery and clinical pharmacotherapy. Most data-driven toxicity models behave as endpoint predictors: they output a label but provide limited transparency about why a compound is risky or which evidence channel dominated the decision.…
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…
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…
Etinosa Osaro, Yamil Colón
The application of machine learning (ML) techniques in materials science has revolutionized the pace and scope of materials research and design. In the case of metal-organic frameworks (MOFs), a promising class of materials due to their tunable properties and versatile applications in gas adsorption and separation, ML…