ORNL

US Department of Energy’s Oak Ridge National Laboratory (ORNL)

MENNDL for Multinode Evolutionary Neural Networks for Deep Learning

For automating certain design aspects for developing artificial neural networks.

MENNDL is a tool for testing and training thousands of potential neural networks to work on unique science problems.

In 2017 MENNDL did an evaluation of 500,000 neural networks in 24 hours to give a solution proved to be superior to custom models developed by human scientists.

Generating a smaller network using the right hyperparameters

Inside the Black Box

Not unlike how the human brain reaches a conclusion, it’s not always possible to understand how a machine, despite being designed by humans, reaches its own solutions. The lack of transparency is often referred to as the AI “black box.” Experts say we can learn something about the evolutionary process of machine learning by generating millions of neural networks and seeing what works well and what doesn’t.

“You’re never going to be able to completely explain what happened, but maybe we can better explain it than we currently can today,” Young said.

Transparency is built into the “thought process” of each particular model generated by Driverless AI,

The computer even explains itself to the user in plain English at each decision point. There is also real-time feedback that allows users to prioritize features, or parameters, to see how the changes improve the accuracy of the model.

One of the advantages of our automatic feature engineering: it’s basically mimicking human thinking, making it statistically significant.