# Symbiotic Hybrid Neural Network Watchdog For Outlier Detection

arXiv: https://arxiv.org/abs/2103.00582 · HTML: https://mlsanity.com/paper/2103.00582/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 26 references that are in the map.
- First posted on arXiv 28 Feb 2021.

## Builds on (most cited first, 2 of 2)

- [A Hybrid Retrieval-Generation Neural Conversation Model](https://mlsanity.com/paper/1904.09068/) (2019)
- [Autoencoder Watchdog Outlier Detection for Classifiers](https://mlsanity.com/paper/2010.12754/) (2020)

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

- [Cascade Watchdog: A Multi-tiered Adversarial Guard for Outlier Detection](https://mlsanity.com/paper/2108.09375/) (2021)
- [Generatively Augmented Neural Network Watchdog for Image Classification Networks](https://mlsanity.com/paper/2109.06168/) (2021)

## Abstract (arXiv)

Neural networks are largely black boxes. A neural network trained to classify fruit may classify a picture of a giraffe as a banana. A neural network watchdog's job is to identify such inputs, allowing a classifier to disregard such data. We investigate whether the watchdog should be separate from the neural network or symbiotically attached. We present empirical evidence that the symbiotic watchdog performs better than when the neural networks are disjoint.