Distributed creation of Machine learning agents for Blockchain analysis
This work addresses the need for efficient and automated AI model creation, potentially democratizing access to AI capabilities across industries, though it appears incremental as it builds on existing NAS methods.
The paper tackles the problem of automating neural network design for cryptocurrency prediction by applying a customized Neural Architecture Search (NAS) algorithm, achieving results on par with manually designed models. It proposes a blockchain network protocol to incentivize distributed NAS execution, aiming to create an autonomous, self-improving source of machine learning models.
Creating efficient deep neural networks involves repetitive manual optimization of the topology and the hyperparameters. This human intervention significantly inhibits the process. Recent publications propose various Neural Architecture Search (NAS) algorithms that automate this work. We have applied a customized NAS algorithm with network morphism and Bayesian optimization to the problem of cryptocurrency predictions, where it achieved results on par with our best manually designed models. This is consistent with the findings of other teams, while several known experiments suggest that given enough computing power, NAS algorithms can surpass state-of-the-art neural network models designed by humans. In this paper, we propose a blockchain network protocol that incentivises independent computing nodes to run NAS algorithms and compete in finding better neural network models for a particular task. If implemented, such network can be an autonomous and self-improving source of machine learning models, significantly boosting and democratizing the access to AI capabilities for many industries.