# Fermi-Bose Machine achieves both generalization and adversarial robustness

arXiv: https://arxiv.org/abs/2404.13631 · HTML: https://mlsanity.com/paper/2404.13631/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 31 references that are in the map.
- First posted on arXiv 21 Apr 2024.

## Builds on (most cited first, 20 of 20)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Adversarial Examples Are Not Bugs, They Are Features](https://mlsanity.com/paper/1905.02175/) (2019)
- [Robustness May Be at Odds with Accuracy](https://mlsanity.com/paper/1805.12152/) (2018)
- [Are adversarial examples inevitable?](https://mlsanity.com/paper/1809.02104/) (2018)
- [Adversarial vulnerability for any classifier](https://mlsanity.com/paper/1802.08686/) (2018)
- [The committee machine: Computational to statistical gaps in learning a two-layers neural network](https://mlsanity.com/paper/1806.05451/) (2018)
- [Precise Statistical Analysis of Classification Accuracies for Adversarial Training](https://mlsanity.com/paper/2010.11213/) (2020)
- [Hierarchical nucleation in deep neural networks](https://mlsanity.com/paper/2007.03506/) (2020)
- [Supervised Hebbian Learning](https://mlsanity.com/paper/2203.01304/) (2022)
- [Semi-Supervised Learning via Compact Latent Space Clustering](https://mlsanity.com/paper/1806.02679/) (2018)
- [Adversarial Examples Might be Avoidable: The Role of Data Concentration in Adversarial Robustness](https://mlsanity.com/paper/2309.16096/) (2023)
- [Eight challenges in developing theory of intelligence](https://mlsanity.com/paper/2306.11232/) (2023)
- [Relationship between manifold smoothness and adversarial vulnerability in deep learning with local errors](https://mlsanity.com/paper/2007.02047/) (2020)
- [Emergence of hierarchical modes from deep learning](https://mlsanity.com/paper/2208.09859/) (2022)
- [Weakly-correlated synapses promote dimension reduction in deep neural networks](https://mlsanity.com/paper/2006.11569/) (2020)

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

- [Network Dynamics-Based Framework for Understanding Deep Neural Networks](https://mlsanity.com/paper/2501.02436/) (2025)
- [Geometric origin of adversarial vulnerability in deep learning](https://mlsanity.com/paper/2509.01235/) (2025)

## Abstract (arXiv)

Distinct from human cognitive processing, deep neural networks trained by backpropagation can be easily fooled by adversarial examples. To design a semantically meaningful representation learning, we discard backpropagation, and instead, propose a local contrastive learning, where the representation for the inputs bearing the same label shrink (akin to boson) in hidden layers, while those of different labels repel (akin to fermion). This layer-wise learning is local in nature, being biological plausible. A statistical mechanics analysis shows that the target fermion-pair-distance is a key parameter. Moreover, the application of this local contrastive learning to MNIST benchmark dataset demonstrates that the adversarial vulnerability of standard perceptron can be greatly mitigated by tuning the target distance, i.e., controlling the geometric separation of prototype manifolds.