# Cluster Flow: how a hierarchical clustering layer make allows deep-NNs more resilient to hacking, more human-like and easily implements relational reasoning

arXiv: https://arxiv.org/abs/2304.14081 · HTML: https://mlsanity.com/paper/2304.14081/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 18 references that are in the map.
- First posted on arXiv 27 Apr 2023.

## Builds on (most cited first, 7 of 7)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges](https://mlsanity.com/paper/2104.13478/) (2021)
- [Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images](https://mlsanity.com/paper/1412.1897/) (2014)
- [Adversarial Patch](https://mlsanity.com/paper/1712.09665/) (2017)
- [Are there any 'object detectors' in the hidden layers of CNNs trained to identify objects or scenes?](https://mlsanity.com/paper/2007.01062/) (2020)
- [Be Careful What You Backpropagate: A Case For Linear Output Activations & Gradient Boosting](https://mlsanity.com/paper/1707.04199/) (2017)

## Abstract (arXiv)

Despite the huge recent breakthroughs in neural networks (NNs) for artificial intelligence (specifically deep convolutional networks) such NNs do not achieve human-level performance: they can be hacked by images that would fool no human and lack `common sense'. It has been argued that a basis of human-level intelligence is mankind's ability to perform relational reasoning: the comparison of different objects, measuring similarity, grasping of relations between objects and the converse, figuring out the odd one out in a set of objects. Mankind can even do this with objects they have never seen before. Here we show how ClusterFlow, a semi-supervised hierarchical clustering framework can operate on trained NNs utilising the rich multi-dimensional class and feature data found at the pre-SoftMax layer to build a hyperspacial map of classes/features and this adds more human-like functionality to modern deep convolutional neural networks. We demonstrate this with 3 tasks. 1. the statistical learning based `mistakes' made by infants when attending to images of cats and dogs. 2. improving both the resilience to hacking images and the accurate measure of certainty in deep-NNs. 3. Relational reasoning over sets of images, including those not known to the NN nor seen before. We also demonstrate that ClusterFlow can work on non-NN data and deal with missing data by testing it on a Chemistry dataset. This work suggests that modern deep NNs can be made more human-like without re-training of the NNs. As it is known that some methods used in deep and convolutional NNs are not biologically plausible or perhaps even the best approach: the ClusterFlow framework can sit on top of any NN and will be a useful tool to add as NNs are improved in this regard.