US 12,175,345 B2
Online machine learning system that continuously learns from data and human input
Tanju Cataltepe, Istanbul (TR)
Assigned to Tazi AI Systems, Inc., San Francisco, CA (US)
Filed by Tazi AI Systems, Inc., Sausalito, CA (US)
Filed on Sep. 9, 2018, as Appl. No. 16/125,744.
Claims priority of provisional application 62/639,490, filed on Mar. 6, 2018.
Prior Publication US 2019/0279043 A1, Sep. 12, 2019
Int. Cl. G06N 20/20 (2019.01); G05B 13/02 (2006.01); G05B 23/02 (2006.01); G06F 3/16 (2006.01); G06F 16/2455 (2019.01); G06F 18/10 (2023.01); G06F 18/15 (2023.01); G06F 18/21 (2023.01); G06F 18/2115 (2023.01); G06F 18/23 (2023.01); G06F 18/40 (2023.01); G06N 3/04 (2023.01); G06N 3/045 (2023.01); G06N 3/08 (2023.01); G06N 5/043 (2023.01); G06N 5/045 (2023.01); G06N 7/00 (2023.01); G06N 20/00 (2019.01); G06V 10/28 (2022.01); G06V 10/70 (2022.01); G06V 10/72 (2022.01); G06V 10/77 (2022.01); G06V 10/778 (2022.01); G06V 10/80 (2022.01)
CPC G06N 20/20 (2019.01) [G05B 13/028 (2013.01); G05B 23/0221 (2013.01); G05B 23/0229 (2013.01); G06F 3/165 (2013.01); G06F 16/24568 (2019.01); G06F 18/10 (2023.01); G06F 18/15 (2023.01); G06F 18/2115 (2023.01); G06F 18/2178 (2023.01); G06F 18/23 (2023.01); G06F 18/40 (2023.01); G06N 3/04 (2013.01); G06N 3/045 (2023.01); G06N 3/08 (2013.01); G06N 5/043 (2013.01); G06N 5/045 (2013.01); G06N 7/00 (2013.01); G06N 20/00 (2019.01); G06V 10/28 (2022.01); G06V 10/70 (2022.01); G06V 10/72 (2022.01); G06V 10/77 (2022.01); G06V 10/778 (2022.01); G06V 10/7784 (2022.01); G06V 10/80 (2022.01); G06V 10/803 (2022.01); G06T 2207/20081 (2013.01)] 16 Claims
OG exemplary drawing
 
1. An Online Machine Learning System (OMLS), the system comprising:
an Online Machine Learning Engine (OMLE) for incorporating and utilizing one or more machine learning algorithms or models utilizing features to generate a result, and capable of incorporating and utilizing multiple different machine learning algorithms;
wherein the OMLS is configured to perform continuous online machine learning, the continuous online machine learning comprising:
continuous online machine learning from streaming data including an instance comprising a vector of inputs, the vector of inputs comprising a plurality of continuous or categorical features; and
continuous online machine learning from expert feedback from an expert;
and wherein:
the continuous online machine learning from streaming data comprises per-instance learning;
the expert feedback comprises model-level expert feedback for the one or more machine learning algorithms or models that is obtained by:
capturing, by the OMLS, a copy of at least one of the one or more machine learning algorithms or models and one or more online explanation models (OEMs) including an online decision tree for model explanations, at a point in time for use as one or more staged models;
wherein the one or more staged models are displayed graphically on an interactive user interface that is configured for interactive model explanation and feedback; and
enabling, by the OMLS, the expert to provide the expert feedback as one or more changes to the one or more staged models using the interactive user interface while the continuous online machine learning from streaming data continues; and
the OMLS is further configured to calculate and adjust continuously the one or more machine learning algorithms or models upon receipt of the expert feedback.