mlsanityData to 7 Oct 2026

SNN-Based Online Learning of Concepts and Action Laws in an Open World

arXiv 2411.12308 ↗First posted 19 Nov 2024cs.AI cs.LG cs.NEcited by 0

Not on the map. Why?

Abstract (arXiv)

We present the architecture of a fully autonomous, bio-inspired cognitive agent built around a spiking neural network (SNN) implementing the agent's semantic memory. This agent explores its universe and learns concepts of objects/situations and of its own actions in a one-shot manner. While object/situation concepts are unary, action concepts are triples made up of an initial situation, a motor activity, and an outcome. They embody the agent's knowledge of its universe's action laws. Both kinds of concepts have different degrees of generality. To make decisions the agent queries its semantic memory for the expected outcomes of envisaged actions and chooses the action to take on the basis of these predictions. Our experiments show that the agent handles new situations by appealing to previously learned general concepts and rapidly modifies its concepts to adapt to environment changes.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 20 of its 47 references that are in the map. First posted on arXiv 19 Nov 2024.

Builds on

20 of 47 references.

References · 20

  1. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  2. 2017Gradient Episodic Memory for Continual Learningcited by 1,871
  3. 2020Concept Bottleneck Modelscited by 1,022
  4. 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 860
  5. 2018Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigencecited by 734
  6. 2019Generalizing from a Few Examples: A Survey on Few-Shot Learningcited by 462
  7. 2020First return, then explorecited by 256
  8. 2021A Survey of Zero-shot Generalisation in Deep Reinforcement Learningcited by 164
  9. 2018Generalization and Regularization in DQNcited by 117
  10. 2019Continual Learning for Robotics: Definition, Framework, Learning Strategies, Opportunities and Challengescited by 92
  11. 2019Interpretable Image Recognition with Hierarchical Prototypescited by 64
  12. 2015Why Neurons Have Thousands of Synapses, A Theory of Sequence Memory in Neocortexcited by 44
8 more
  1. 2019Dealing with Sparse Rewards in Reinforcement Learningcited by 40
  2. 2018Learning Features and Abstract Actions for Computing Generalized Planscited by 35
  3. 2016STDP-based spiking deep convolutional neural networks for object recognitioncited by 24
  4. 2015Continuous online sequence learning with an unsupervised neural network modelcited by 18
  5. 2023Concept Learning for Interpretable Multi-Agent Reinforcement Learningcited by 18
  6. 2022HINT: Hierarchical Neuron Concept Explainercited by 17
  7. 2023State2Explanation: Concept-Based Explanations to Benefit Agent Learning and User Understandingcited by 17
  8. 2024A survey on Concept-based Approaches For Model Improvementcited by 8

Built on by

Not cited yet.