22 papers · ranked by Valyu relevance
Sandeep Madireddy, Ángel Yanguas-Gil, Prasanna Balaprakash
The ability to learn and adapt in real time is a central feature of biological systems. Neuromorphic architectures demonstrating such versatility can greatly enhance our ability to efficiently process information at the edge. A key challenge, however, is to understand which learning rules are best suited for specific…
Christian Albers, Maren Westkott, Klaus Pawelzik, Maurice J. Chacron
Precise spatio-temporal patterns of neuronal action potentials underly e.g. sensory representations and control of muscle activities. However, it is not known how the synaptic efficacies in the neuronal networks of the brain adapt such that they can reliably generate spikes at specific points in time. Existing…
Sankhanava Kundu, Daniel keren, Samma Zidan, Amit Kumar + 2 more
Training rodents in a particularly difficult olfactory-discrimination task results with acquisition of high skill to perform the task superbly, termed ‘rule-learning’. We show that rule-learning occurs abruptly, in a “light bulb moment”. Using whole-cell patch-clamp recordings in the piriform cortex of…
Mathieu Galtier, Gilles Wainrib
Identifying, formalizing and combining biological mechanisms which implement known brain functions, such as prediction, is a main aspect of current research in theoretical neuroscience. In this letter, the mechanisms of Spike Timing Dependent Plasticity (STDP) and homeostatic plasticity, combined in an original…
Amir Levi, Noam Aviv, Eran Stark
Learning from examples and adapting to new rules are fundamental attributes of human cognition. However, it is unclear what conditions allow for fast and successful learning, especially in non-human subjects. To determine how rapidly freely-moving mice can learn a new rule, we designed a fully automated two-alternative…
Joshua S. Rule, Steven T. Piantadosi, Andrew Cropper, Kevin Ellis + 2 more
Throughout their lives, humans seem to learn a variety of rules for things like applying category labels, following procedures, and explaining causal relationships. These rules are often algorithmically rich but are nonetheless acquired with minimal data and computation. Symbolic models based on program learning…
František Malinka, Filip železný, Jiří Kléma
Background Identification of non-trivial and meaningful patterns in omics data is one of the most important biological tasks. The patterns help to better understand biological systems and interpret experimental outcomes. A well-established method serving to explain such biological data is Gene Set Enrichment Analysis.…
Yarden Cohen, Elad Schneidman, Rony Paz
Primates can quickly and advantageously adopt complex rule-based behaviors. We studied acquisition of a classification task while recording single neurons in the dorsal-anterior-cingulate-cortex (dACC) and the Striatum. Monkeys performed trial-by-trial classification on a rich set of multicue patterns, allowing de-novo…
Matthew Balcarras, Thilo Womelsdorf
Learning in a new environment is influenced by prior learning and experience. Correctly applying a rule that maps a context to stimuli, actions, and outcomes enables faster learning and better outcomes compared to relying on strategies for learning that are ignorant of task structure. However, it is often difficult to…
Florian Bähner, Tzvetan Popov, Nico Boehme, Selina Hermann + 6 more
Rapid learning in complex and changing environments is a hallmark of intelligent behavior. Humans achieve this in part through abstract concepts applicable to multiple, related situations. It is unclear, however, whether some of the underlying computational mechanisms also exist in other species. We combined…
Florian Beck, Johannes Fürnkranz
Inductive rule learning is arguably among the most traditional paradigms in machine learning. Although we have seen considerable progress over the years in learning rule-based theories, all state-of-the-art learners still learn descriptions that directly relate the input features to the target concept. In the simplest…
Sungyong Seo, Sercan Ö. Arık, Jinsung Yoon, X. D. Zhang + 2 more
'Kihyuk Sohn' 'Tomas Pfister'] We propose a novel training method that integrates rules into deep learning, in a way the strengths of the rules are controllable at inference. Deep Neural Networks with Controllable Rule Representations (DEEPCTRL) incorporates a rule encoder into the model coupled with a rule-based…
F. Bouchacourt, S. Tafazoli, M.G. Mattar, T.J. Buschman + 1 more
When performing a task in a changing world, sometimes we switch between rules already learned; at other times we must learn rules anew. Often we must do both, switching between known rules while also constantly re-estimating them. Here, we show these two processes, rule switching and rule learning, rely on distinct but…
Florian Beck, Johannes Fürnkranz
Inductive rule learning is arguably among the most traditional paradigms in machine learning. Although we have seen considerable progress over the years in learning rule-based theories, all state-of-the-art learners still learn descriptions that directly relate the input features to the target concept. In the simplest…
Vicki M. Bier, Paul B. Kantor, Gary Lupyan, Xiaojin Zhu
What makes a task relatively more or less difficult for a machine compared to a human? Much AI/ML research has focused on expanding the range of tasks that machines can do, with a focus on whether machines can beat humans. Allowing for differences in scale, we can seek interesting (anomalous) pairs of tasks T, T'. We…
Lincen Yang, Matthijs van Leeuwen
Rule set learning has long been studied and has recently been frequently revisited due to the need for interpretable models. Still, existing methods have several shortcomings: 1) most recent methods require a binary feature matrix as input, while learning rules directly from numeric variables is understudied; 2)…
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…
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…
Authors not listed
Step-by-step thinking is essential in all domains of chemical sciences and engineering. While machine learning tools are broadly used, algorithms that automate reasoning are far less common. We elaborate on seven categories of human reasoning activities and connect each to applications in chemical science and…
Authors not listed
Data-driven strategies are reshaping computational materials design by accelerating the prediction of novel compounds with targeted functionalities. Beyond high-throughput screening, the integration of generative artificial intelligence enables exploration across vast chemical spaces comprising millions of known and…
Friedrich Hastedt, Rowan M. Bailey, Klaus Hellgardt, Sophia N. Yaliraki + 2 more
Machine learning models for chemical retrosynthesis have attracted substantial interest in recent years. Unaddressed challenges, particularly the absence of robust evaluation metrics for performance comparison, and the lack of black-box interpretability, obscure model limitations and impede progress in the field. We…
Authors not listed
SynTemp is a framework designed to extract and hierarchically cluster reaction templates from large-scale reaction data repositories. Reaction templates are partial Imaginary Transition State graphs representing the reaction center as well as surrounding context. These graphs are equivalent to Double Pushout graph…