Supercharge Your Innovation With Domain-Expert AI Agents!

Autonomous modification of data

A technology for modifying data and data samples, applied in the field of machine learning systems and computer program products, and can solve problems such as difficulty in training machine learning systems

Pending Publication Date: 2020-10-30
IBM CORP
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, it turns out that the training of machine learning systems is not easy, it is a highly complex process, success or failure depends on the availability of training data

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
  • Autonomous modification of data
  • Autonomous modification of data
  • Autonomous modification of data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] In the context of this description, the following conventions, terms and / or expressions may be used:

[0027] The term "generative adversarial network" (GAN) denotes a class of machine learning systems. Two neural networks can compete against each other in a zero-sum game framework. The technique can generate, for example, photos with many real features that appear at least superficially real to a human observer. It can represent a form of unsupervised learning.

[0028] A generative network, or generator network, can generate candidates, while a discriminative network evaluates these candidates. Competitions can be played on data distribution. Typically, a generative network can learn to map from the hidden space to the data distribution of interest, while a discriminative network can distinguish the candidates generated by the generator from the real data distribution. The training goal of a generative network may be to increase the error rate of the discriminator...

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

The invention relates to autonomous modification of data. A computer-implemented method for modifying patterns in datasets using a generative adversarial network may be provided. The method comprisesproviding pairs of data samples. The pairs comprise each a base data sample and a modified data sample. Thereby, the modified pattern is determined by applying random modifications to the base data sample. Additionally, the method comprises training of the generator for building a model of the generator using an adversarial training method and using the pairs of data samples as input, wherein thediscriminator receives as input dataset pairs of datasets, the dataset pairs comprising each a prediction output of the generator based on a base data sample and the corresponding modified data sample, thereby optimizing a joint loss function for the generator and the discriminator, and predicting an output dataset for unknown data samples as input for the generator without the discriminator.

Description

technical field [0001] The present invention relates generally to autonomously altering patterns in data, and more specifically, to a computer-implemented method for modifying patterns in datasets using generative adversarial networks. The invention also relates to a corresponding machine learning system and computer program product for modifying patterns in a dataset using a generative adversarial network. Background technique [0002] Artificial intelligence (AI), in the form of special machine learning, is widely introduced in enterprise deployments and as part of enterprise applications. Currently, software development is undergoing a transition from linear programming to machine learning (ML) model training. However, training a machine learning system has proven to be non-trivial, a highly complex process whose success or failure depends on the availability of training data. The prediction results of a machine learning system are only as good as the results of the tra...

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
IPC IPC(8): G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06N3/088G06N3/047G06N20/20
Inventor A·乔万尼尼A·F·罗德里格斯M·加布拉尼A·克里斯塔利迪斯
Owner IBM CORP
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com