ON THE USE OF CONVOLUTIONAL AUTO-ENCODER FOR INCREMENTAL CLASSIFIER LEARNING IN CONTEXT AWARE ADVERTISEMENT

Tin Lay Nwe, Shudong Xie, Balaji Nataraj, Yiqun Li, Joo-Hwee Lim

Abstract:

Context Aware Advertisement (CAA) is a type of advertisement
appearing on websites or mobile apps. The advertisement is targeted
on specific group of users and/or the content displayed on the
websites or apps. This paper focuses on classifying images displayed
on the websites by incremental learning classifier with Deep
Convolutional Neural Network (DCNN) especially for Context Aware
Advertisement (CAA) framework. Incrementally learning new knowledge
with DCNN leads to catastrophic forgetting as previously stored
information is replaced with new information. To prevent
catastrophic forgetting, part of previously learned knowledge should
be stored for the life time of incremental classifier. Storing
information for life time involves privacy and legal concerns
especially in context aware advertising framework. Here, we propose
an incremental classifier learning method which addresses privacy
and legal concerns while taking care of catastrophic forgetting
problem. We conduct experiments on different datasets including
CIFAR-100. Experimental results show that proposed system achieves
relatively high performance compared to the state-of-the-art
incremental learning methods.

Keywords: Incremental learning, deep learning, autoencoder, privacy, convolutional neural network

TL;DR: Human brain inspired incremental learning system

Data: [CIFAR-100](https://paperswithcode.com/dataset/cifar-100)