(162b) Automated Machine Learning - Paving the Way to True Generalization with Evolutionary Methods

Automated machine learning has the potential to reduce the burden
on already overwhelmed teams by automating the main bottlenecks
in the data science process, but too many autoML applications are
simply automating flawed or legacy processes.

To address this need, SparkCognitionâ„¢ has developed the Darwinâ„¢
platform, an automated machine learning product that accelerates
data science at scale, enabling you to assess the quality of your
dataset and advising you on how to fix problems to make it suitable
for the model-building process. Darwin then automates time-consuming
tasks that range from model creation and optimization to
model deployment and continuous maintenance.

Most autoML solutions in the market today focus on searching for
the best algorithm to fit a given data set. However, these methods
can be restrictive, lacking the ability to produce novel, elegant model
architectures to solve new problems.

The next evolution in autoML is the ability to create models that do
not follow predefined formulas, but rather adapt and evolve according
to the problem’s data. This is the fundamental operating principle
of the Darwinâ„¢ software.