Distributed creation of Machine learning agents for Blockchain analysis

09/06/2019
by   Zvezdin Besarabov, et al.
14

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.

READ FULL TEXT

page 2

page 5

page 6

page 7

research
06/27/2018

Efficient Neural Architecture Search with Network Morphism

While neural architecture search (NAS) has drawn increasing attention fo...
research
07/04/2021

Mutation is all you need

Neural architecture search (NAS) promises to make deep learning accessib...
research
10/30/2020

AgEBO-Tabular: Joint Neural Architecture and Hyperparameter Search with Autotuned Data-Parallel Training for Tabular Data

Developing high-performing predictive models for large tabular data sets...
research
08/30/2022

Neural Architecture Search for Improving Latency-Accuracy Trade-off in Split Computing

This paper proposes a neural architecture search (NAS) method for split ...
research
12/03/2020

Automatic Routability Predictor Development Using Neural Architecture Search

The rise of machine learning technology inspires a boom of its applicati...
research
12/17/2020

On the performance of deep learning for numerical optimization: an application to protein structure prediction

Deep neural networks have recently drawn considerable attention to build...
research
06/22/2018

Deep SNP: An End-to-end Deep Neural Network with Attention-based Localization for Break-point Detection in SNP Array Genomic data

Diagnosis and risk stratification of cancer and many other diseases requ...

Please sign up or login with your details

Forgot password? Click here to reset