scholarly journals Optimal structure of metaplasticity for adaptive learning

2017 ◽  
Author(s):  
Peyman Khorsand ◽  
Alireza Soltani
Keyword(s):  
Adaptive Learning ◽  
Synaptic Efficacy ◽  
Learning Models ◽  
Strong Signal ◽  
Precise Estimation ◽  
Rapid Changes ◽  
Synaptic Changes ◽  
Reinforcement Learning Models ◽  
Reward Information ◽  
High Degree

AbstractLearning from reward feedback in a changing environment requires a high degree of adaptability, yet the precise estimation of reward information demands slow updates. We show that this tradeoff between adaptability and precision, which is present in standard reinforcement-learning models, can be substantially overcome via reward-dependent metaplasticity (reward-dependent synaptic changes that do not always alter synaptic efficacy). Metaplastic synapses achieve both adaptability and precision by forming two separate sets of meta-states: reservoirs and buffers. Synapses in reservoir meta-states do not change their efficacy upon reward feedback, whereas those in buffer meta-states can change their efficacy. Rapid changes in efficacy are limited to synapses occupying buffers, creating a bottleneck that reduces noise without significantly decreasing adaptability. In contrast, more-populated reservoirs can generate a strong signal without manifesting any observable plasticity. We suggest that ubiquitous unreliability of synaptic changes evinces metaplasticity that can provide a robust mechanism for adaptive learning.

Bayes factors for reinforcement-learning models of the Iowa gambling task.

Decision ◽  
2016 ◽  
Vol 3 (2) ◽  
pp. 115-131 ◽  
Author(s):  
Helen Steingroever ◽  
Ruud Wetzels ◽  
Eric-Jan Wagenmakers
Keyword(s):  
Reinforcement Learning ◽  
Iowa Gambling Task ◽  
Bayes Factors ◽  
Gambling Task ◽  
Learning Models ◽  
Reinforcement Learning Models

scholarly journals Striatal and hippocampal contributions to flexible navigation in rats and humans

2020 ◽  
Vol 4 ◽  
pp. 239821282097977
Author(s):  
Christoffer J. Gahnstrom ◽  
Hugo J. Spiers
Keyword(s):  
Caudate Nucleus ◽  
Spatial Navigation ◽  
Dorsal Striatum ◽  
Future Research ◽  
Neural Responses ◽  
Learning Models ◽  
Transition Structure ◽  
Cortical Areas ◽  
Reinforcement Learning Models ◽  
Human Neuroimaging

The hippocampus has been firmly established as playing a crucial role in flexible navigation. Recent evidence suggests that dorsal striatum may also play an important role in such goal-directed behaviour in both rodents and humans. Across recent studies, activity in the caudate nucleus has been linked to forward planning and adaptation to changes in the environment. In particular, several human neuroimaging studies have found the caudate nucleus tracks information traditionally associated with that by the hippocampus. In this brief review, we examine this evidence and argue the dorsal striatum encodes the transition structure of the environment during flexible, goal-directed behaviour. We highlight that future research should explore the following: (1) Investigate neural responses during spatial navigation via a biophysically plausible framework explained by reinforcement learning models and (2) Observe the interaction between cortical areas and both the dorsal striatum and hippocampus during flexible navigation.

scholarly journals Test-retest reliability of canonical reinforcement learning models

2019 ◽  
Author(s):  
Laura Weidinger ◽  
Andrea Gradassi ◽  
Lucas Molleman ◽  
Wouter van den Bos
Keyword(s):  
Reinforcement Learning ◽  
Learning Models ◽  
Retest Reliability ◽  
Reinforcement Learning Models ◽  
Test Retest Reliability

scholarly journals Unsupervised by any other name: Hidden layers of knowledge production in artificial intelligence on social media

2019 ◽  
Vol 6 (1) ◽  
pp. 205395171881956 ◽  
Author(s):  
Anja Bechmann ◽  
Geoffrey C Bowker
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Knowledge Production ◽  
Classification Theory ◽  
Human Knowledge ◽  
Learning Models ◽  
Work Process ◽  
Learning Development ◽  
High Degree ◽  
Machine Learning Models

Artificial Intelligence (AI) in the form of different machine learning models is applied to Big Data as a way to turn data into valuable knowledge. The rhetoric is that ensuing predictions work well—with a high degree of autonomy and automation. We argue that we need to analyze the process of applying machine learning in depth and highlight at what point human knowledge production takes place in seemingly autonomous work. This article reintroduces classification theory as an important framework for understanding such seemingly invisible knowledge production in the machine learning development and design processes. We suggest a framework for studying such classification closely tied to different steps in the work process and exemplify the framework on two experiments with machine learning applied to Facebook data from one of our labs. By doing so we demonstrate ways in which classification and potential discrimination take place in even seemingly unsupervised and autonomous models. Moving away from concepts of non-supervision and autonomy enable us to understand the underlying classificatory dispositifs in the work process and that this form of analysis constitutes a first step towards governance of artificial intelligence.

Educational Technology Standards

2011 ◽  
pp. 413-425
Author(s):  
Michael O’Dea
Keyword(s):  
Learning Environments ◽  
Adaptive Learning ◽  
Educational Program ◽  
Approaches To Learning ◽  
Technology Standards ◽  
Learning Models ◽  
Student Records ◽  
Teaching Institution ◽  
E Learning ◽  
Pedagogical Approaches

The “holy grail” of e-learning is to enable individualized, flexible, adaptive learning environments that support different learning models or pedagogical approaches to learning to allow any Internet-connected user to undertake an educational program. It is also very highly desirable, from a more practical viewpoint, if this environment can also integrate into the wider MIS/student records system of the teaching institution.

Sign in / Sign up

Export Citation Format

Share Document