22 papers · ranked by Valyu relevance
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…
Mingcan Yu, Junying Wang
Although principles of neuroscience like reinforcement learning, visual perception and attention have been applied in machine learning models, there is a huge gap between machine learning and mammalian learning. Based on the advances in neuroscience, we propose the "context sequence theory" to give a common explanation…
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…
Sophie Peterson, Jose Chavira, Alex Garcia Arango, David Seamans + 2 more
Reward cues are often ambiguous; what is good in one context is not necessarily good in another context. To solve this ambiguity, animals form hierarchical associations in which the context acts as a gatekeeper in the retrieval of the appropriate cue-evoked memory, ensuring context-appropriate behavior. These…
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.…
Sia Hranova, Stefan Kiebel, Michael N. Smolka, Sarah Schwöbel
Humans have a remarkable ability to act efficiently and accurately in familiar situations while remaining flexible in novel circumstances. Nonparametric contextual inference has been proposed as a computational principle that can model how agents achieve flexible yet stable behaviour in dynamic and possibly unknown…
Weichen Zhou, Xia Wu
With the popularity of learning vocabulary online among English as a Foreign Language (EFL) learners today, educators and researchers have been considering ways to enhance the effectiveness of this approach. Prior research has underscored the significance of contextual clues in vocabulary acquisition. However, few…
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…
Gido M. van de Ven, Nicholas Soures, Dhireesha Kudithipudi
This book chapter delves into the dynamics of continual learning, which is the process of incrementally learning from a non-stationary stream of data. Although continual learning is a natural skill for the human brain, it is very challenging for artificial neural networks. An important reason is that, when learning…
Marcus Sefranek, Nahid Zokaei, Dejan Draschkow, Anna C. Nobre
During visual search, we quickly learn to attend to an object’s likely location. Research has shown that this process can be guided by learning target locations based on consistent spatial contextual associations or statistical regularities. Here, we tested how these different types of learning aid the utilisation of…
Wen Su, Guang Zhao, Jie Ma
1## Introduction In our daily lives, we are surrounded by a wealth of visual information that integrates with surrounding elements to form a “scene” or “context.” Previous research has highlighted the facilitative role of context in visual search (). Individuals can locate a target (e.g., a car) more rapidly in a…
Durstewitz, Daniel, Averbeck, Bruno + 2 more
Modern AI models, such as large language models, are usually trained once on a huge corpus of data, potentially fine-tuned for a specific task, and then deployed with fixed parameters. Their training is costly, slow, and gradual, requiring billions of repetitions. In stark contrast, animals continuously adapt to the…
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.…
Zhengyu Hu, Jianxun Lian, Zheyuan Xiao, Seraphina Zhang + 5 more
Zhengyu Hu1, 2 , Jianxun Lian3 ∗ , Zheyuan Xiao1, 2 , Seraphina Zhang 4 , Tianfu Wang1, 2 , Nicholas Jing Yuan 5 , Xing Xie 3 , Hui Xiong1, 2 1 Thrust of Artificial Intelligence, The Hong Kong University of Science and Technology (Guangzhou), China 2 Department of Computer Science and Engineering, The Hong Kong…
Tameem Adel
Continual learning is an online paradigm where a learner continually accumulates knowledge from different tasks encountered over sequential time steps. Importantly, the learner is required to extend and update its knowledge without forgetting about the learning experience acquired from the past, and while avoiding the…
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…
Atith Gandhi, Raj Sanjay Shah, Vijay Marupudi, Sashank Varma
Neural networks often suffer from catastrophic interference (CI): performance on previously learned tasks drops off significantly when learning a new task. This contrasts strongly with humans, who can continually learn new tasks without appreciably forgetting previous tasks. Prior work has explored various techniques…
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…
Xiaoqian Liu, Junge Zhang, Mingyi Zhang, Peipei Yang
tinuously acquiring and transferring knowledge without catastrophic forgetting of old concepts. While humans achieve continual learning via diverse neurocognitive mechanisms, there is a mismatch between cognitive properties and evaluation methods of continual learning models. First, the measurement of continual…
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…