mlsanityData to 14 Oct 2026

Polarity is all you need to learn and transfer faster

arXiv 2303.17589 ↗First posted 29 Mar 2023cs.LG cs.CV cs.NEcited by 2

Not on the map. Why?

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.

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

15 of 32 references.

References · 15

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  4. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  5. 2018The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networkscited by 2,262
  6. 2016Matching Networks for One Shot Learningcited by 2,255
  7. 2014Deep metric learning using Triplet networkcited by 422
  8. 2019Deconstructing Lottery Tickets: Zeros, Signs, and the Supermaskcited by 207
  9. 2022Error-driven Input Modulation: Solving the Credit Assignment Problem without a Backward Passcited by 63
  10. 2020Iterative label cleaning for transductive and semi-supervised few-shot learningcited by 40
  11. 2021On the Existence of Universal Lottery Ticketscited by 30
  12. 2018Deep learning with asymmetric connections and Hebbian updatescited by 16
3 more
  1. 2022EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredientscited by 16
  2. 2021How to Train Your Wide Neural Network Without Backprop: An Input-Weight Alignment Perspectivecited by 13
  3. 2022Why do networks have inhibitory/negative connections?cited by 4

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 1.

2 papers.

  1. 2024Masks, Signs, And Learning Rate Rewindingcited by 15
  2. 2025Find A Winning Sign: Sign Is All We Need to Win the Lotterycited by 1