24 papers · ranked by Valyu relevance
Dorothée B. Hoppe, Petra Hendriks, Michael Ramscar, Jacolien van Rij
Error-driven learning algorithms, which iteratively adjust expectations based on prediction error, are the basis for a vast array of computational models in the brain and cognitive sciences that often differ widely in their precise form and application: they range from simple models in psychology and cybernetics to…
Yicong Zheng, Xiaonan L. Liu, Satoru Nishiyama, Charan Ranganath + 2 more
'Randall C. O’Reilly' 'Alireza Soltani'] The hippocampus plays a critical role in the rapid learning of new episodic memories. Many computational models propose that the hippocampus is an autoassociator that relies on Hebbian learning (i.e., “cells that fire together, wire together”). However, Hebbian learning is…
Yicong Zheng, Xiaonan L. Liu, Satoru Nishiyama, Charan Ranganath + 1 more
The hippocampus plays a critical role in the rapid learning of new episodic memories. Many computational models propose that the hippocampus is an autoassociator that relies on Hebbian learning (i.e., “cells that fire together, wire together”). However, Hebbian learning is computationally suboptimal as it modifies…
Shih-pi Ku, Eric L. Hargreaves, Sylvia Wirth, Wendy A. Suzuki
Computational models proposed that the medial temporal lobe (MTL) contributes importantly to error-driven learning, though little direct in-vivo evidence for this hypothesis exists. To test this, we recorded in the entorhinal cortex (EC) and hippocampus (HPC) as macaques performed an associative learning task using an…
P. Dylan Rich, Stephan Y. Thiberge, Nathaniel D. Daw, David W. Tank
Flexible behavior requires both the learning of new associations, and the suppression of previous ones, but how neural circuits achieve this balance remains unclear. Here we show that continuous changes in hippocampal representations, known as drift, may facilitate this process. We used voluntary head-fixation and…
Yan Liu, Erik D. Reichle
Although different learning systems are coordinated to afford complex behavior, little is known about how this occurs. This article describes a theoretical framework that specifies how complex behaviors that might be thought to require error-driven learning might instead be acquired through simple reinforcement. This…
Rasmus Bruckner, Hauke R. Heekeren, Matthew R. Nassar
Learning allows humans and other animals to make predictions about the environment that facilitate adaptive behavior. Casting learning as predictive inference can shed light on normative cognitive mechanisms that improve predictions under uncertainty. Drawing on normative learning models, we illustrate how learning…
Naser Al-Fawakhiri, Sarosh Kayani, Samuel D. McDougle
When acquiring a motor skill, learners must practice the skill at a difficulty that is challenging but still manageable in order to gradually improve their performance. In other words, during training the learner must experience success as well as failure. Does there exist an optimal proportion of successes and…
Krishnan Raghavan, Vignesh Narayanan, Jagannathan Saraangapani
— Learning to control complex systems using nontraditional feedback, e.g., in the form of snapshot images, is an important task encountered in diverse domains such as robotics, neuroscience, and biology (cellular systems). In this paper, we present a two neural-network (NN)-based feedback control framework to design…
Naser Al-Fawakhiri, Sarosh Kayani, Samuel D. McDougle
When acquiring a motor skill, learners must practice the skill at a difficulty that is challenging but still manageable to gradually improve their performance. In other words, during training, the learner must experience success as well as failure. Does there exist an optimal proportion of successes and failures to…
Samuel J. Gershman
Where do objective functions come from? How do we select what goals to pursue? Human intelligence is adept at synthesizing new objective functions on the fly. How does this work, and can we endow artificial systems with the same ability? This paper proposes an approach to answering these questions, starting with the…
Erdem Pulcu
We are living in a dynamic world in which stochastic relationships between cues and outcome events create different sources of uncertainty^1^ (e.g. the fact that not all grey clouds bring rain). Living in an uncertain world continuously probes learning systems in the brain, guiding agents to make better decisions. This…
Steven Miletić, Russell J Boag, Anne C Trutti, Niek Stevenson + 4 more
Learning and decision-making are interactive processes, yet cognitive modeling of error-driven learning and decision-making have largely evolved separately. Recently, evidence accumulation models (EAMs) of decision-making and reinforcement learning (RL) models of error-driven learning have been combined into joint…
Taisei Sugiyama, Nicolas Schweighofer, Jun Izawa
Humans and animals develop learning-to-learn strategies throughout their lives to accelerate learning. One theory suggests that this is achieved by a metacognitive process of controlling and monitoring learning. Although such learning-to-learn is also observed in motor learning, the metacognitive aspect of learning…
Esther Heid, Charles J. McGill, Florence H. Vermeire, William H. Green
Characterizing uncertainty in machine learning models has recently gained interest in the context of machine learning reliability, robustness, safety, and active learning. Here, we separate the total uncertainty into contributions from noise in the data (aleatoric) and shortcomings of the model (epistemic), further…
Maier, Antoine, Maier, Aude + 2 more
—A common but rarely examined assumption in machine learning is that training yields models that actually satisfy their specified objective function. We call this the Objective Satisfaction Assumption (OSA). Although deviations from OSA are acknowledged, their implications are overlooked. We argue, in a…
Inês Lourenço, Rebecka Winqvist, Cristian R. Rojas, Bo Wahlberg
— A classical learning setting typically concerns an agent/student who collects data, or observations, from a system in order to estimate a certain property of interest. Correctional learning is a type of cooperative teacher-student framework where a teacher, who has partial knowledge about the system, has the ability…
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…
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…
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…
Anestis Fachantidis, Matthew E. Taylor, Ioannis Vlahavas
—In this article we study the transfer learning model of action advice under a budget. We focus on reinforcement learning teachers providing action advice to heterogeneous students playing the game of Pac-Man under a limited advice budget. First, we examine several critical factors affecting advice quality in this…
Authors not listed
Developing generalizable machine learning models with minimal data remains a central challenge in materials informatics. Effective models can significantly reduce costly computational simulations and time-intensive experimentation by providing reliable predictions of material properties. In this work, we investigate…
Authors not listed
Nonadiabatic couplings (NACs) play a crucial role in modeling photochemical and photophysical processes with methods such as the widely used fewest-switches surface hopping (FSSH). There is therefore a strong incentive to machine learn NACs for accelerating simulations. However, this is challenging due to NACs’…
Yun‐Shiuan Chuang, Xuezhou Zhang, Yuzhe Ma, Mark K. Ho + 2 more
'Joseph L. Austerweil' 'Junwei Zhu'] Successful teaching requires an assumption of how the learner learns - how the learner uses experiences from the world to update their internal states. We investigate what expectations people have about a learner when they teach them in an online manner using rewards and punishment.…