Conformal Prediction Framework

• Small memory and energy footprint
• Works on top of any machine learning model of Ekkono’s SDK
• Aids towards validation of evolving systems
• Confidence bounds are guaranteed to contain the correct output value with some pre-defined probability
• Necessary for sensitive and high-risk applications

Input(s):

• Regression datasets

Main feature(s):

• Machine Learning framework for constructing predictive models that can estimate the confidence of their own predictions
• Used on top of machine learning models, as built-in quality assurance
• Good for safety-critical systems

Output(s):

• Model predictions in the form of confidence intervals

The framework is part of the Ekkono SDK:

• Modeling: .NET 2.0+ or Python 3.7+ (Windows, macOS, or Linux)
• Deployment: C++17 (or C++14 with included MPark.Variant), delivered as source to be compiled by the customer
• Integration will be done through Ekkono’s C++ API of the compiled library

Data Scientists, machine learning engineers, and software developers that want to run machine learning and conformal prediction on any type of device.

Commercial license