# Understanding Locally Competitive Networks

arXiv: https://arxiv.org/abs/1410.1165 · HTML: https://mlsanity.com/paper/1410.1165/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Oct 2014.

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

- [Interpreting Neural Networks through the Polytope Lens](https://mlsanity.com/paper/2211.12312/) (2022)
- [From Diet to Free Lunch: Estimating Auxiliary Signal Properties using Dynamic Pruning Masks in Speech Enhancement Networks](https://mlsanity.com/paper/2602.10666/) (2026)

## Abstract (arXiv)

Recently proposed neural network activation functions such as rectified linear, maxout, and local winner-take-all have allowed for faster and more effective training of deep neural architectures on large and complex datasets. The common trait among these functions is that they implement local competition between small groups of computational units within a layer, so that only part of the network is activated for any given input pattern. In this paper, we attempt to visualize and understand this self-modularization, and suggest a unified explanation for the beneficial properties of such networks. We also show how our insights can be directly useful for efficiently performing retrieval over large datasets using neural networks.