Related Experiment Video
Updated: Apr 20, 2026

Shuttle Box Assay as an Associative Learning Tool for Cognitive Assessment in Learning and Memory Studies using Adult Zebrafish
Published on: July 12, 2021
A high-capacity model for one shot association learning in the brain
Hafsteinn Einarsson1, Johannes Lengler1, Angelika Steger2
1Department of Computer Science, Institute of Theoretical Computer Science, ETH Zürich Zürich, Switzerland.
This study introduces a high-capacity model for one-shot association learning in sparse neural networks. The model efficiently learns hundreds of associations from single presentations, enhancing brain-like network capabilities.
Area of Science:
- Computational neuroscience
- Artificial intelligence
- Network science
Background:
- One-shot association learning is crucial for efficient information processing in biological and artificial systems.
- Sparse neural networks offer a biologically plausible framework for complex cognitive functions.
- Existing models often struggle with high capacity and immediate learning from single instances.
Purpose of the Study:
- To develop a high-capacity model for one-shot hetero-associative memory in sparse networks.
- To investigate the learning capacity and retrieval enhancement through iterative processes.
- To provide a computationally efficient model for brain-like neural networks.
Main Methods:
- Combining Amit-Fusi and Willshaw type networks with sparse connectivity.
- Employing a palimpsest learning procedure adapted for one-shot pattern association.
- Utilizing iterative retrieval to enhance network capacity.
- Analyzing model performance using bootstrap percolation theory on random graphs.
Main Results:
- The proposed model demonstrates high capacity, learning hundreds of associations with single presentations.
- Iterative retrieval significantly enhances the associative learning capacity of the sparse network.
- The model effectively simulates brain-like networks with populations of a few thousand neurons.
- Theoretical analysis confirms the model's robustness and capacity through percolation theory.
Conclusions:
- The developed model offers a significant advancement in one-shot association learning for sparse neural networks.
- This framework provides a scalable and efficient approach for modeling memory in brain-like systems.
- The findings have implications for developing more sophisticated artificial memory systems and understanding biological learning.
More Related Videos
08:43Combined Shuttle-Box Training with Electrophysiological Cortex Recording and Stimulation as a Tool to Study Perception and Learning
Published on: October 22, 2015
09:22A Method for Remotely Silencing Neural Activity in Rodents During Discrete Phases of Learning
Published on: June 22, 2015
Related Concept Videos
Associative Learning
Classical conditioning, also known...
Higher Mental Functions of Brain: Learning and Memory
Association Areas of the Cortex
Prefrontal Association Area: This area is located in the frontal lobe and is involved in planning, decision-making, and moderating social behavior. It connects with primary motor areas,...