Limiting the Reconstruction Capability of Generative Neural Network using Negative Learning

TL;DR

This paper introduces a negative learning technique to restrict generative neural networks to produce only specific inputs, enhancing applications like anomaly detection and obstacle recognition.

Contribution

The paper presents a novel negative learning method that limits a generative network's output to desired inputs, improving its effectiveness in anomaly detection and related tasks.

Findings

Enhanced anomaly detection performance on MNIST dataset

Effective restriction of generative outputs to specific input types

Successful application to real-world obstacle detection

Abstract

Generative models are widely used for unsupervised learning with various applications, including data compression and signal restoration. Training methods for such systems focus on the generality of the network given limited amount of training data. A less researched type of techniques concerns generation of only a single type of input. This is useful for applications such as constraint handling, noise reduction and anomaly detection. In this paper we present a technique to limit the generative capability of the network using negative learning. The proposed method searches the solution in the gradient direction for the desired input and in the opposite direction for the undesired input. One of the application can be anomaly detection where the undesired inputs are the anomalous data. In the results section we demonstrate the features of the algorithm using MNIST handwritten digit dataset and latter apply the technique to a real-world obstacle detection problem. The results clearly show that the proposed learning technique can significantly improve the performance for anomaly detection.