Active Machine Learning
First Claim
1. A method comprising:
- initiating active machine learning through an active machine learning system configured to train an auxiliary machine learning model to produce at least one new labeled observation;
refining a target machine learning model based at least on the active machine learning, wherein the target machine learning model includes a limited-capacity machine learning model; and
retraining the auxiliary machine learning model with the at least one new labeled observation subsequent to refining the capacity of the target machine learning model.
2 Assignments
0 Petitions
Accused Products
Abstract
Technologies are described herein for active machine learning. An active machine learning method can include initiating active machine learning through an active machine learning system configured to train an auxiliary machine learning model to produce at least one new labeled observation, refining a capacity of a target machine learning model based on the active machine learning, and retraining the auxiliary machine learning model with the at least one new labeled observation subsequent to refining the capacity of the target machine learning model. Additionally, the target machine learning model is a limited-capacity machine learning model according to the description provided herein.
-
Citations
20 Claims
-
1. A method comprising:
-
initiating active machine learning through an active machine learning system configured to train an auxiliary machine learning model to produce at least one new labeled observation; refining a target machine learning model based at least on the active machine learning, wherein the target machine learning model includes a limited-capacity machine learning model; and retraining the auxiliary machine learning model with the at least one new labeled observation subsequent to refining the capacity of the target machine learning model. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11)
-
-
12. A computer-readable medium having computer-executable instructions thereupon that, when executed by a computer, cause the computer to perform operations comprising:
-
selecting an unlabeled observation from a pool of unlabeled observations through an auxiliary machine learning model, wherein it is not known to which one of a plurality of classes the unlabeled observation belongs; converting the unlabeled observation to a new labeled observation based on an output of the auxiliary machine learning model responsive to the unlabeled observation; refining a capacity of a target machine learning model based on the converting, wherein the target machine learning model is a limited-capacity machine learning model; and retraining the auxiliary machine learning model with the new labeled observation subsequent to refining the capacity of the target machine learning model. - View Dependent Claims (13, 14, 15, 16)
-
-
17. An active machine learning system, the system comprising:
-
an auxiliary machine learning model configured to assign a first score to an unlabeled observation; a target machine learning model configured to assign a second score to the unlabeled observation, wherein the target machine learning model and the auxiliary machine learning model are from different machine learning model classes, and wherein the target machine learning model is a limited-capacity machine learning model; a comparison component configured to compare the first score and the second score to determine a probability that the target machine learning model has returned a false positive or a false negative result; and a featuring component configured to receive the output of the comparison component. - View Dependent Claims (18, 19, 20)
-
Specification