# On Modifying a Neural Network's Perception

arXiv: https://arxiv.org/abs/2303.02655 · HTML: https://mlsanity.com/paper/2303.02655/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 35 references that are in the map.
- First posted on arXiv 5 Mar 2023.

## Builds on (most cited first, 13 of 13)

- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [Explanation in Artificial Intelligence: Insights from the Social Sciences](https://mlsanity.com/paper/1706.07269/) (2017)
- [Explaining Explanations: An Overview of Interpretability of Machine Learning](https://mlsanity.com/paper/1806.00069/) (2018)
- [A Survey of the Recent Architectures of Deep Convolutional Neural Networks](https://mlsanity.com/paper/1901.06032/) (2019)
- [Debugging Tests for Model Explanations](https://mlsanity.com/paper/2011.05429/) (2020)
- [How Useful Are the Machine-Generated Interpretations to General Users? A Human Evaluation on Guessing the Incorrectly Predicted Labels](https://mlsanity.com/paper/2008.11721/) (2020)
- [What if This Modified That? Syntactic Interventions via Counterfactual Embeddings](https://mlsanity.com/paper/2105.14002/) (2021)
- [Are Visual Explanations Useful? A Case Study in Model-in-the-Loop Prediction](https://mlsanity.com/paper/2007.12248/) (2020)
- [ECINN: Efficient Counterfactuals from Invertible Neural Networks](https://mlsanity.com/paper/2103.13701/) (2021)
- [Generative Counterfactuals for Neural Networks via Attribute-Informed Perturbation](https://mlsanity.com/paper/2101.06930/) (2021)
- [Explainable Abstract Trains Dataset](https://mlsanity.com/paper/2012.12115/) (2020)

## Built on by (most cited first, 1 of 1)

- [Concept-Based Explanations in Computer Vision: Where Are We and Where Could We Go?](https://mlsanity.com/paper/2409.13456/) (2024)

## Abstract (arXiv)

Artificial neural networks have proven to be extremely useful models that have allowed for multiple recent breakthroughs in the field of Artificial Intelligence and many others. However, they are typically regarded as black boxes, given how difficult it is for humans to interpret how these models reach their results. In this work, we propose a method which allows one to modify what an artificial neural network is perceiving regarding specific human-defined concepts, enabling the generation of hypothetical scenarios that could help understand and even debug the neural network model. Through empirical evaluation, in a synthetic dataset and in the ImageNet dataset, we test the proposed method on different models, assessing whether the performed manipulations are well interpreted by the models, and analyzing how they react to them.