Towards Neural Network Patching: Evaluating Engagement-Layers and Patch-Architectures

12/09/2018
by   Sebastian Kauschke, et al.
0

In this report we investigate fundamental requirements for the application of classifier patching [8] on neural networks. Neural network patching is an approach for adapting neural network models to handle concept drift in nonstationary environments. Instead of creating or updating the existing network to accommodate concept drift, neural network patching leverages the inner layers of the network as well as its output to learn a patch that enhances the classification and corrects errors caused by the drift. It learns (i) a predictor that estimates whether the original network will misclassify an instance, and (ii) a patching network that fixes the misclassification. Neural network patching is based on the idea that the original network can still classify a majority of instances well, and that the inner feature representations encoded in the deep network aid the classifier to cope with unseen or changed inputs. In order to apply this kind of patching, we evaluate different engagement layers and patch architectures in this report, and find a set of generally applicable heuristics, which aid in parametrizing the patching procedure.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/19/2022

A Sequential Concept Drift Detection Method for On-Device Learning on Low-End Edge Devices

A practical issue of edge AI systems is that data distributions of train...
research
06/05/2023

The Learning Prescription, A Neural Network Hearing Aid Core

The definition of a hearing aid core which is based on a prescription ne...
research
02/28/2021

A Proof of Concept Neural Network Watchdog using a Hybrid Generative Classifier For Optimized Outlier Detection

With the continuous development of tools such as TensorFlow and PyTorch,...
research
06/11/2018

Understanding Patch-Based Learning by Explaining Predictions

Deep networks are able to learn highly predictive models of video data. ...
research
06/22/2022

Concentration inequalities and optimal number of layers for stochastic deep neural networks

We state concentration and martingale inequalities for the output of the...
research
12/12/2022

Carpet-bombing patch: attacking a deep network without usual requirements

Although deep networks have shown vulnerability to evasion attacks, such...

Please sign up or login with your details

Forgot password? Click here to reset