Artificial Intelligence Guided Research and Development

a technology of artificial intelligence and research and development, applied in the field of artificial intelligence, can solve the problems of insufficient handling of high-dimensional problems with many experimental parameters, haphazard selection of experiments, and inability to clearly integrate or prioritize all the different combinations

Pending Publication Date: 2022-04-14
UNCOUNTABLE INC
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Benefits of technology

This approach systematically generates and prioritizes experiments, ensuring a more comprehensive exploration of parameter variations and improving the efficiency of experimentation by focusing on experiments with higher predicted success rates.

Problems solved by technology

Oftentimes, the lists of goals and adjustable experimental parameters are long and diverse, and it may not be clear how to incorporate or prioritize all the different combinations to be tried.
Moreover, these techniques insufficiently handle high-dimensional problems with many experimental parameters.
This approach eschews statistical modeling in favor of experimenter intuition and results in a haphazardly selected set of experiments that may not adequately test enough variations of parameters.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Artificial Intelligence Guided Research and Development
  • Artificial Intelligence Guided Research and Development
  • Artificial Intelligence Guided Research and Development

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0015]The figures and the following description relate to preferred embodiments by way of illustration only. It should be noted that from the following discussion, alternative embodiments of the structures and methods disclosed herein will be readily recognized as viable alternatives that may be employed without departing from the principles of what is claimed.

[0016]A preferred embodiment includes a multi-component software system with which an experimenter interacts. FIG. 1 outlines the steps of one example of a development testing process that a development team might use. Information about the development task is entered 110. This may include a definition of the development task, such as the experiment parameters that may be varied, the outcome variables and the desired goals or specifications. Existing experimental data is also entered 120 into the software system. The software system uses machine learning algorithms to train 130 a predictive model using that data. The software ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

Recommendations for new experiments are generated via a pipeline that includes a predictive model and a preference procedure. In one example, a definition of a development task includes experiment parameters that may be varied, the outcomes of interest and the desired goals or specifications. Existing experimental data is used by machine learning algorithms to train a predictive model. The software system generates candidate experiments and uses the trained predictive model to predict the outcomes of the candidate experiments based on their parameters. A merit function (referred to as a preference function) is calculated for the candidate experiments. The preference function is a function of the experiment parameters and / or the predicted outcomes. It may also be a function of features that are derived from these quantities. The candidate experiments are ranked based on the preference function.

Description

CROSS-REFERENCE TO RELATED APPLICATION(S)[0001]This application is a continuation of U.S. patent application Ser. No. 16 / 104,774, “Artificial Intelligence Guided Research and Development,” filed Aug. 17, 2018; which claims priority under 35 U.S.C. § 119(e) to U.S. Provisional Patent Application Ser. No. 62 / 547,723, “Artificial Intelligence Guided Research and Development,” filed Aug. 18, 2017. The subject matter of all of the foregoing is incorporated herein by reference in their entirety.BACKGROUND1. Technical Field[0002]This disclosure relates generally to artificial intelligence used to recommend experiments, for example for materials or process development.2. Description of the Related Art[0003]Industrial research and development teams are often tasked with developing a new material or process that meets a specific set of specifications or goals. An experimenter will run experiments that try different combinations of process parameters and compositions of ingredients. The experi...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & AuthorityApplications(United States)
IPC IPC(8): G06N5/04G06N3/12G06N20/10
CPCG06N5/04G06N20/20G06N20/10G06N3/126G06N3/084G06N7/01
InventorHIRSHMAN, JASON ISAACHOLLINGSWORTH, NOELTASHMAN, WILL
OwnerUNCOUNTABLE INC