mlsanityData to 7 Oct 2026

Randomly Weighted Neuromodulation in Neural Networks Facilitates Learning of Manifolds Common Across Tasks

arXiv 2401.02437 ↗First posted 17 Nov 2023cs.NE cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Geometric Sensitive Hashing functions, a family of Local Sensitive Hashing functions, are neural network models that learn class-specific manifold geometry in supervised learning. However, given a set of supervised learning tasks, understanding the manifold geometries that can represent each task and the kinds of relationships between the tasks based on them has received little attention. We explore a formalization of this question by considering a generative process where each task is associated with a high-dimensional manifold, which can be done in brain-like models with neuromodulatory systems. Following this formulation, we define Task-specific Geometric Sensitive Hashing~(T-GSH) and show that a randomly weighted neural network with a neuromodulation system can realize this function.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 12 of its 24 references that are in the map. First posted on arXiv 17 Nov 2023.

Builds on

12 of 24 references.

References · 12

  1. 2017Random Erasing Data Augmentationcited by 1,235
  2. 2019Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networkscited by 562
  3. 2018Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layerscited by 340
  4. 2016Toward Deeper Understanding of Neural Networks: The Power of Initialization and a Dual View on Expressivitycited by 138
  5. 2016A Survey on Learning to Hashcited by 119
  6. 2020Backpropamine: training self-modifying neural networks with differentiable neuromodulated plasticitycited by 39
  7. 2020Deep Reinforcement Learning and its Neuroscientific Implicationscited by 33
  8. 2018Introducing Neuromodulation in Deep Neural Networks to Learn Adaptive Behaviourscited by 16
  9. 2021For Manifold Learning, Deep Neural Networks can be Locality Sensitive Hash Functionscited by 6
  10. 2021An Insect-Inspired Randomly, Weighted Neural Network with Random Fourier Features For Neuro-Symbolic Relational Learningcited by 5
  11. 2021Representing Prior Knowledge Using Randomly, Weighted Feature Networks for Visual Relationship Detectioncited by 3
  12. 2022Learning to Modulate Random Weights: Neuromodulation-inspired Neural Networks For Efficient Continual Learningcited by 3

Built on by

Not cited yet.