Novelty Detection Through Model-Based Characterization of Neural Networks

by   Gukyeong Kwon, et al.

In this paper, we propose a model-based characterization of neural networks to detect novel input types and conditions. Novelty detection is crucial to identify abnormal inputs that can significantly degrade the performance of machine learning algorithms. Majority of existing studies have focused on activation-based representations to detect abnormal inputs, which limits the characterization of abnormality from a data perspective. However, a model perspective can also be informative in terms of the novelties and abnormalities. To articulate the significance of the model perspective in novelty detection, we utilize backpropagated gradients. We conduct a comprehensive analysis to compare the representation capability of gradients with that of activation and show that the gradients outperform the activation in novel class and condition detection. We validate our approach using four image recognition datasets including MNIST, Fashion-MNIST, CIFAR-10, and CURE-TSR. We achieve a significant improvement on all four datasets with an average AUROC of 0.953, 0.918, 0.582, and 0.746, respectively.


q-Space Novelty Detection with Variational Autoencoders

In machine learning, novelty detection is the task of identifying novel ...

Backpropagated Gradient Representations for Anomaly Detection

Learning representations that clearly distinguish between normal and abn...

Generative Models for Novelty Detection: Applications in abnormal event and situational change detection from data series

Novelty detection is a process for distinguishing the observations that ...

Toward A Neuro-inspired Creative Decoder

Creativity, a process that generates novel and valuable ideas, involves ...

OCmst: One-class Novelty Detection using Convolutional Neural Network and Minimum Spanning Trees

We present a novel model called One Class Minimum Spanning Tree (OCmst) ...

Automated Detection of Abnormal EEGs in Epilepsy With a Compact and Efficient CNN Model

Electroencephalography (EEG) is essential for the diagnosis of epilepsy,...

A Unifying Framework for Formal Theories of Novelty:Framework, Examples and Discussion

Managing inputs that are novel, unknown, or out-of-distribution is criti...