Combining Optimal Path Search With Task-Dependent Learning in a Neural Network

TL;DR

This paper introduces a neural network approach to pathfinding that mimics classical algorithms like Bellman-Ford and can adapt paths through learning mechanisms, enabling task-specific path optimization.

Contribution

It presents a neural network model that transforms path costs into weights, allowing online adaptation and integration of learning with classical pathfinding algorithms.

Findings

Neural network solutions match Bellman-Ford algorithm results.

Network weights can be adapted via Hebbian learning.

The approach enables task-dependent path augmentation.

Abstract

Finding optimal paths in connected graphs requires determining the smallest total cost for traveling along the graph's edges. This problem can be solved by several classical algorithms where, usually, costs are predefined for all edges. Conventional planning methods can, thus, normally not be used when wanting to change costs in an adaptive way following the requirements of some task. Here we show that one can define a neural network representation of path finding problems by transforming cost values into synaptic weights, which allows for online weight adaptation using network learning mechanisms. When starting with an initial activity value of one, activity propagation in this network will lead to solutions, which are identical to those found by the Bellman-Ford algorithm. The neural network has the same algorithmic complexity as Bellman-Ford and, in addition, we can show that network learning mechanisms (such as Hebbian learning) can adapt the weights in the network augmenting the resulting paths according to some task at hand. We demonstrate this by learning to navigate in an environment with obstacles as well as by learning to follow certain sequences of path nodes. Hence, the here-presented novel algorithm may open up a different regime of applications where path-augmentation (by learning) is directly coupled with path finding in a natural way.