Randomly Weighted Neuromodulation in Neural Networks Facilitates Learning of Manifolds Common Across Tasks
This work addresses a gap in analyzing manifold relationships across tasks, which could benefit multi-task learning in AI, though it appears incremental as it builds on existing Geometric Sensitive Hashing functions.
The paper tackles the problem of understanding manifold geometries across multiple supervised learning tasks by formalizing each task as a high-dimensional manifold and introducing Task-specific Geometric Sensitive Hashing (T-GSH). It shows that a randomly weighted neural network with neuromodulation can realize T-GSH, facilitating learning of common manifolds across tasks.
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 \emph{Task-specific Geometric Sensitive Hashing~(T-GSH)} and show that a randomly weighted neural network with a neuromodulation system can realize this function.