Statistical Measures For Defining Curriculum Scoring Function

TL;DR

This paper introduces statistical measures like standard deviation and entropy to score data difficulty for curriculum learning, demonstrating improved neural network performance on image classification tasks.

Contribution

It presents a simple statistical scoring method for curriculum learning and proposes a dynamic algorithm that adaptively selects training examples based on gradient direction.

Findings

Statistical difficulty measures improve classification performance.

Dynamic curriculum algorithm accelerates convergence.

Curriculum learning enhances neural network training efficiency.

Abstract

Curriculum learning is a training strategy that sorts the training examples by some measure of their difficulty and gradually exposes them to the learner to improve the network performance. Motivated by our insights from implicit curriculum ordering, we first introduce a simple curriculum learning strategy that uses statistical measures such as standard deviation and entropy values to score the difficulty of data points for real image classification tasks. We empirically show its improvements in performance with convolutional and fully-connected neural networks on multiple real image datasets. We also propose and study the performance of a dynamic curriculum learning algorithm. Our dynamic curriculum algorithm tries to reduce the distance between the network weight and an optimal weight at any training step by greedily sampling examples with gradients that are directed towards the optimal weight. Further, we use our algorithms to discuss why curriculum learning is helpful.