# Generation of Paths in a Maze using a Deep Network without Learning

arXiv: https://arxiv.org/abs/2004.00540 · HTML: https://mlsanity.com/paper/2004.00540/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Apr 2020.

## Built on by (most cited first, 2 of 2)

- [Pathfinding Neural Cellular Automata](https://mlsanity.com/paper/2301.06820/) (2023)
- [Combining Optimal Path Search With Task-Dependent Learning in a Neural Network](https://mlsanity.com/paper/2201.11104/) (2022)

## Abstract (arXiv)

Trajectory- or path-planning is a fundamental issue in a wide variety of applications. Here we show that it is possible to solve path planning for multiple start- and end-points highly efficiently with a network that consists only of max pooling layers, for which no network training is needed. Different from competing approaches, very large mazes containing more than half a billion nodes with dense obstacle configuration and several thousand path end-points can this way be solved in very short time on parallel hardware.