NeuNetS: An Automated Synthesis Engine for Neural Network Design
Abstract
Application of neural networks to a vast variety of practical applications is transforming the way AI is applied in practice. Pre-trained neural network models available through APIs or capability to custom train pre-built neural network architectures with customer data has made the consumption of AI by developers much simpler and resulted in broad adoption of these complex AI models. While prebuilt network models exist for certain scenarios, to try and meet the constraints that are unique to each application, AI teams need to think about developing custom neural network architectures that can meet the tradeoff between accuracy and memory footprint to achieve the tight constraints of their unique use-cases. However, only a small proportion of data science teams have the skills and experience needed to create a neural network from scratch, and the demand far exceeds the supply. In this paper, we present NeuNetS : An automated Neural Network Synthesis engine for custom neural network design that is available as part of IBM's AI OpenScale's product. NeuNetS is available for both Text and Image domains and can build neural networks for specific tasks in a fraction of the time it takes today with human effort, and with accuracy similar to that of human-designed AI models.
Cite
@article{arxiv.1901.06261,
title = {NeuNetS: An Automated Synthesis Engine for Neural Network Design},
author = {Atin Sood and Benjamin Elder and Benjamin Herta and Chao Xue and Costas Bekas and A. Cristiano I. Malossi and Debashish Saha and Florian Scheidegger and Ganesh Venkataraman and Gegi Thomas and Giovanni Mariani and Hendrik Strobelt and Horst Samulowitz and Martin Wistuba and Matteo Manica and Mihir Choudhury and Rong Yan and Roxana Istrate and Ruchir Puri and Tejaswini Pedapati},
journal= {arXiv preprint arXiv:1901.06261},
year = {2019}
}
Comments
14 pages, 12 figures. arXiv admin note: text overlap with arXiv:1806.00250