# Polarity is all you need to learn and transfer faster

arXiv: https://arxiv.org/abs/2303.17589 · HTML: https://mlsanity.com/paper/2303.17589/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 32 references that are in the map.
- First posted on arXiv 29 Mar 2023.

## Builds on (most cited first, 15 of 15)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Deep metric learning using Triplet network](https://mlsanity.com/paper/1412.6622/) (2014)
- [Deconstructing Lottery Tickets: Zeros, Signs, and the Supermask](https://mlsanity.com/paper/1905.01067/) (2019)
- [Error-driven Input Modulation: Solving the Credit Assignment Problem without a Backward Pass](https://mlsanity.com/paper/2201.11665/) (2022)
- [Iterative label cleaning for transductive and semi-supervised few-shot learning](https://mlsanity.com/paper/2012.07962/) (2020)
- [On the Existence of Universal Lottery Tickets](https://mlsanity.com/paper/2111.11146/) (2021)
- [Deep learning with asymmetric connections and Hebbian updates](https://mlsanity.com/paper/1812.07965/) (2018)
- [EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients](https://mlsanity.com/paper/2201.09699/) (2022)
- [How to Train Your Wide Neural Network Without Backprop: An Input-Weight Alignment Perspective](https://mlsanity.com/paper/2106.08453/) (2021)
- [Why do networks have inhibitory/negative connections?](https://mlsanity.com/paper/2208.03211/) (2022)

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

- [Masks, Signs, And Learning Rate Rewinding](https://mlsanity.com/paper/2402.19262/) (2024)
- [Find A Winning Sign: Sign Is All We Need to Win the Lottery](https://mlsanity.com/paper/2504.05357/) (2025)

## Abstract (arXiv)

Natural intelligences (NIs) thrive in a dynamic world - they learn quickly, sometimes with only a few samples. In contrast, artificial intelligences (AIs) typically learn with a prohibitive number of training samples and computational power. What design principle difference between NI and AI could contribute to such a discrepancy? Here, we investigate the role of weight polarity: development processes initialize NIs with advantageous polarity configurations; as NIs grow and learn, synapse magnitudes update, yet polarities are largely kept unchanged. We demonstrate with simulation and image classification tasks that if weight polarities are adequately set a priori, then networks learn with less time and data. We also explicitly illustrate situations in which a priori setting the weight polarities is disadvantageous for networks. Our work illustrates the value of weight polarities from the perspective of statistical and computational efficiency during learning.