Title: Generative memory for lifelong machine learning

Abstract

Techniques are disclosed for training machine learning systems. An input device receives training data comprising pairs of training inputs and training labels. A generative memory assigns training inputs to each archetype task of a plurality of archetype tasks, each archetype task representative of a cluster of related tasks within a task space and assigns a skill to each archetype task. The generative memory generates, from each archetype task, auxiliary data comprising pairs of auxiliary inputs and auxiliary labels. A machine learning system trains a machine learning model to apply a skill assigned to an archetype task to training and auxiliary inputs assigned to the archetype task to obtain output labels corresponding to the training and auxiliary labels associated with the training and auxiliary inputs assigned to the archetype task to enable scalable learning to obtain labels for new tasks for which the machine learning model has not previously been trained.

Inventors:

Nadamuni Raghavan, Aswin; Hostetler, Jesse; Sur, Indranil; Rahman, Abrar Abdullah; Chai, Sek Meng

Issue Date:

2022-11-08

Research Org.:

SRI International, Menlo Park, CA (United States)

Sponsoring Org.:

USDOE; Defense Advanced Research Projects Agency (DARPA)

OSTI Identifier:

1986789

Patent Number(s):

11494597

Application Number:

16/825,953

Assignee:

SRI International (Menlo Park, CA)

Patent Classifications (CPCs):

G - PHYSICS G06 - COMPUTING G06F - ELECTRIC DIGITAL DATA PROCESSING

G - PHYSICS G06 - COMPUTING G06N - COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS

Show more

G - PHYSICS G06 - COMPUTING G06F - ELECTRIC DIGITAL DATA PROCESSING

G06F3/0659 - {Command handling arrangements, e.g. command buffers, queues, command scheduling}
G06F9/3836 - {Instruction issuing, e.g. dynamic instruction scheduling, out of order instruction execution}
G06F9/48 - Program initiating

G - PHYSICS G06 - COMPUTING G06N - COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS

G06N20/00 - Machine learning
G06N3/0409 - {Adaptive resonance theory [ART] networks}
G06N3/08 - Learning methods
G06N3/088 - {Non-supervised learning, e.g. competitive learning}

G - PHYSICS G06 - COMPUTING G06Q - DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES

G06Q40/08 - Insurance, e.g. risk analysis or pensions {

Show less

DOE Contract Number:  

HR0011-18-C-0051

Resource Type:

Patent

Resource Relation:

Patent File Date: 03/20/2020

Country of Publication:

United States

Language:

English