Randomly Weighted Neuromodulation In Neural Networks Facilitates Learning Of Manifolds Common Across Tasks

Abstract

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.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyhong2023randomly

Related papers

• For Manifold Learning, Deep Neural Networks Can Be Locality Sensitive Hash Functions (2021)0.00
• Connecting Neural Models Latent Geometries With Relative Geodesic Representations (2025)0.00
• Unsupervised Domain-adaptive Hash For Networks (2021)0.00
• Mining On Manifolds: Metric Learning Without Labels (2018)14.31
• Latent Functional Maps: A Spectral Framework For Representation Alignment (2024)3.58
• Cascading Hierarchical Networks With Multi-task Balanced Loss For Fine-grained Hashing (2023)0.00
• Task-adaptive Asymmetric Deep Cross-modal Hashing (2020)9.41
• Regularizing Deep Hashing Networks Using GAN Generated Fake Images (2018)0.00