System and method for interpretable sequence and time-series data modeling

Abstract

A novel interpretable and steerable deep sequence modeling technique is disclosed. The technique combines prototype learning and RNNs to achieve both interpretability and high accuracy. Experiments and case studies on different real-world sequence prediction / classification tasks demonstrate that the model is not only as accurate as other state-of-the-art machine learning techniques but also much more interpretable. In addition, a large-scale user study on Amazon Mechanical Turk demonstrates that for familiar domains like sentiment analysis on texts, the model is able to select high quality prototypes that are well aligned with human knowledge for prediction and interpretation. Furthermore, the model obtains better interpretability without a loss of performance by incorporating the feedbackfrom a user study to update the prototypes, demonstrating the benefits of involving human-in-the-loop for interpretable machine learning.

Description

[0001] Cross References to Related Applications [0002] This application claims the benefit of U.S. Provisional Application Serial No. 62 / 849,669 filed May 17, 2019, the contents of which are hereby incorporated by reference in their entirety. technical field [0003] The present application generally relates to a system for generating interpretive information for use in decisions made by machine learning algorithms. Background technique [0004] Increased use of machine learning in devices and computing systems to make decisions or predictions. Despite their practical utility, machine learning algorithms often lack transparency, which limits their use in many critical decision-making scenarios. The need for more transparent and understandable machine learning systems has become more urgent due to recent regulations in the European Union requiring a "right to interpretation" over the algorithms used to make individual-level predictions. Contents of the invention [0005...

AI Technical Summary

Problems solved by technology

Despite their practical utility, machine learning algorithms often lack transparency, which limits their use in many critical decision-making scenarios

Images