NEAP-F: Network Epoch Accuracy Prediction Framework (Student Abstract)

Authors

  • Arushi Chauhan IIIT Delhi
  • Mayank Vatsa IIT Jodhpur
  • Richa Singh IIT Jodhpur

Keywords:

Deep Learning, Performance Prediction, Neural Architecture Search, Network Architecture, Accuracy, Image Datasets, Skip Connections

Abstract

Recent work in neural architecture search has spawned interest in algorithms that can predict the performance of convolutional neural networks using minimum time and computation resources. We propose a new framework, Network Epoch Accuracy Prediction Framework (NEAP-F) which can predict the testing accuracy achieved by a convolutional neural network in one or more epochs. We introduce a novel approach to generate vector representations for networks, and encode ``ease" of classifying image datasets into a vector. For vector representations of networks, we focus on the layer parameters and connections between the network layers. A network achieves different accuracies on different image datasets; therefore, we use the image dataset characteristics to create a vector signifying the ``ease" of classifying the image dataset. After generating these vectors, the prediction models are trained with architectures having skip connections seen in current state-of-the-art architectures. The framework predicts accuracies in order of milliseconds, demonstrating its computational efficiency. It can be easily applied to neural architecture search methods to predict the performance of candidate networks and can work on unseen datasets as well.

Downloads

Published

2021-05-18

How to Cite

Chauhan, A., Vatsa, M., & Singh, R. (2021). NEAP-F: Network Epoch Accuracy Prediction Framework (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 35(18), 15767-15768. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17880

Issue

Section

AAAI Student Abstract and Poster Program