Meta-Learning System for Machine Learning Model Search

Solution Overview

Problem

Large machine learning problems require significant computational resources and time to search for effective solutions, as traditional methods involve testing numerous models and blueprints, leading to inefficiencies and high power consumption.

Innovation Solution

A meta-learning system that leverages knowledge from past machine learning projects to efficiently identify and deploy high-performing blueprints and models by searching through existing projects, reducing the need to develop and train numerous models, thus saving resources and time.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If traditional machine learning search methods are used to find effective solutions, then solution quality can be improved, but computational resources and time consumption increase significantly

Engineering Contradiction:

Improvesolution qualityVSAvoidsearch time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary actions by collecting and storing performance data from multiple machine learning solutions applied to various problems in advance. This pre-collected data forms a dataset that can be quickly queried later, avoiding the need to perform extensive search and evaluation at the time of need, thus resolving the contradiction between solution quality and search time.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system creates copies of performance data and results from previously tested machine learning solutions. Instead of re-evaluating solutions from scratch, the system queries and utilizes these stored performance copies, significantly reducing the time required to find effective solutions while maintaining solution quality.

Inventive Principle:

Principle #26Copying

2Reliability

If traditional machine learning search methods are used to find effective solutions, then solution quality can be improved, but computational resource usage increases significantly

Engineering Contradiction:

Improvesolution qualityVSAvoidcomputational resources

Core Design Contradiction:

ReliabilityVSQuantity of substance

Solution Approach 1:

The system performs preliminary actions by collecting and storing performance data from multiple machine learning solutions applied to various problems in advance. This pre-collected data forms a dataset that can be quickly queried later, avoiding the need to perform extensive search and evaluation at the time of need, thus resolving the contradiction between solution quality and search time.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system creates copies of performance data and results from previously tested machine learning solutions. Instead of re-evaluating solutions from scratch, the system queries and utilizes these stored performance copies, significantly reducing the time required to find effective solutions while maintaining solution quality.

Inventive Principle:

Principle #26Copying

3Reliability

If traditional machine learning search methods are used to find effective solutions, then solution quality can be improved, but power consumption increases significantly

Engineering Contradiction:

Improvesolution qualityVSAvoidpower consumption

Core Design Contradiction:

ReliabilityVSUse of energy by moving object

Solution Approach 1:

The system performs preliminary actions by collecting and storing performance data from multiple machine learning solutions applied to various problems in advance. This pre-collected data forms a dataset that can be quickly queried later, avoiding the need to perform extensive search and evaluation at the time of need, thus resolving the contradiction between solution quality and search time.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system creates copies of performance data and results from previously tested machine learning solutions. Instead of re-evaluating solutions from scratch, the system queries and utilizes these stored performance copies, significantly reducing the time required to find effective solutions while maintaining solution quality.

Inventive Principle:

Principle #26Copying

Data Source

PatentUS20230394361A1Machine learning model search using meta data

Publication Date: 2023.12.07 DATAROBOT INC

AI summary

Machine learning model searching using meta data is provided. A system receives, via a graphical user interface from a client device, a request to search for one or more blueprints including one or more models to add to a project. The system can identify, based on a selection, a list of features with which to execute the requested search. The system can provide a blueprint including a model selected from projects established via input from client devices different from the client device, the projects including blueprints, the blueprints including models trained by machine learning. The system can train, via machine learning, the model of the blueprint to determine the target and add the blueprint including the trained model to the project. The system can generate data causing the graphical user interface to display an indication of the blueprint including the trained model.