Image Classification by Reinforcement Learning with Two-State Q-Learning

EasyChair Preprint 4052

Abstract

In this paper, a simple and efficient Hybrid Classifier is presented which is based on deep learning and reinforcement learning. Q-Learning has been used with two states and 'two or three' actions. Other techniques found in the literature use feature map extracted from Convolutional Neural Networks and use these in the Q-states along with past history. This leads to technical difficulties in these approaches because the number of states is high due to large dimensions of the feature map. Because our technique uses only two Q-states it is straightforward and consequently has much lesser number of optimisation parameters, and thus also has a simple reward function. Also, the proposed technique uses novel actions for processing images as compared to other techniques found in literature. The performance of the proposed technique is compared with other recent algorithms like ResNet50, InceptionV3, etc. on popular databases including ImageNet, Cats and Dogs Dataset, and Caltech-101 Dataset. Our approach outperforms others techniques on all the datasets used.

Keyphrases: ImageNet, InceptionV3, Q-learning, Reinforcement Learning, ResNet50, deep learning, image classification

@booklet{EasyChair:4052,
  author    = {Abdul Mueed Hafiz and Ghulam Mohiuddin Bhat},
  title     = {Image Classification by Reinforcement Learning with Two-State Q-Learning},
  howpublished = {EasyChair Preprint 4052},
  year      = {EasyChair, 2020}}