Oct, 25 2019 13:28 JST

Source: Fujitsu Ltd

Fujitsu Develops Technology for Maintaining Stable, High-Accuracy AI Operations

Accurate annotation of changing data to automate AI accuracy estimation and restoration

KAWASAKI, Japan, Oct, 25 2019 - (JCN Newswire) - Fujitsu Laboratories, Ltd., has announced the development of the world's first "High Durability Learning" technology that estimates the accuracy of AI and automatically restores AI models. In a business context, AI models often struggle to maintain accuracy over the course of operations due to frequent changes in input data caused by shifts in social conditions and market trends. The newly developed technology makes it possible to automatically estimate the accuracy of the AI model during operations while preventing deterioration of its accuracy.

Figure 1. Challenges in AI Operations (Examples of credit risk assessment in the financial sector)
 

Figure 2. Automatically annotation of input data with High Durability Learning
 


This technology enables AI models to be maintained with high accuracy over a long period and enables stable AI operations in various circumstances. This technology will be offered as part of Fujitsu's Human Centric AI Zinrai, a comprehensive portfolio that encompasses Fujitsu's wide range of AI technologies and techniques.

Development Background

As AI models built from training data find additional uses in business, shifts in social conditions, market trends, and the environment can lead to changes in input data from the time when the model was initially trained. This causes deterioration of the accuracy of an AI model. When evaluating corporate credit risk in the financial sector using an AI model trained with corporate financial data, for instance, the accuracy of credit risk estimates will gradually deteriorate. This is because the tendencies of input data into the system will change over time after the model was initially trained due to broader trends in the economy. This makes it essential to periodically check the accuracy of AI models being used for business. If deterioration of the accuracy is confirmed, the AI model must be retrained using the latest data to restore the accuracy of its predictions.

Issues

Measuring the accuracy of the AI model requires the latest input data (Example: Financial Data) and the labeled data set (Example: Credit Risk). Preparing the labeled data is costly and labor-intensive, and it sometimes requires experts to annotate correct labels to large amounts of data. It is also difficult to determine when AI models should be retrained and it may be difficult to detect even if accuracy decreases significantly until its deterioration has actually been confirmed (Figure 1).

About the Newly Developed Technology

Fujitsu has developed a "High Durability Learning" technology that can estimate the accuracy of an AI model at any time during its operation and automatically restore it when deterioration of its accuracy is detected. The features of the developed technology are as follows.

1. Estimation of AI model's accuracy during operation

Correct labels can be automatically annotated to input data during operations by visually charting the distribution of training data used to train an AI model and the distribution of input data during operations, as well as by grasping tendencies of changes in data from the time of training to the time the model is used (Figure 2). This makes it possible to estimate the accuracy of the AI model at that point in time by comparing the estimated results of the original AI model against the input data with the automatically configured correct labels.

2. Controlling reductions inaccuracy by automatically restoring the AI model

Based on the correct labels given to the input data, the decision boundary of the AI model can be adjusted according to trends of the input data, so that the AI model can automatically adapt to the new input data. As a result, it is possible to effectively prevent decreases of the accuracy of AI model without performing retraining.

Effects

Using financial data from 3,800 companies, Fujitsu has verified our assessment of credit risk in the financial sector. This technology has made it possible to estimate the accuracy of AI model within a 3% error margin. We also confirmed that this technology can maintain the accuracy of AI at 89%, which was at 69% with the conventional technology. The new technology can maintain the accuracy of AI model over a long period, delivering reliable and stable operations for users. Fujitsu anticipates that its High Durability Learning technology will ultimately improve the efficiency of AI models not only in the financial sector but in various other businesses, as well, including for product classification in the retail sector and character recognition in the distribution and logistics sector.

Future Plans

Fujitsu aims to incorporate this technology into its goal-oriented "Design the Trusted Future by Data x AI" processes and framework, as well as for machine learning technologies in its Zinrai portfolio, and aiming to deliver practical use cases by the end of FY 2020.

About Fujitsu Laboratories

Founded in 1968 as a wholly-owned subsidiary of Fujitsu Limited, Fujitsu Laboratories Ltd. is one of the premier research centers in the world. With a global network of laboratories in Japan, China, the United States and Europe, the organization conducts a wide range of basic and applied research in the areas of Next-generation Services, Computer Servers, Networks, Electronic Devices, and Advanced Materials. For more information, please see http://www.fujitsu.com/jp/group/labs/en/.


About Fujitsu Ltd
Fujitsu is the leading Japanese information and communication technology (ICT) company, offering a full range of technology products, solutions, and services. Approximately 132,000 Fujitsu people support customers in more than 100 countries. We use our experience and the power of ICT to shape the future of society with our customers. Fujitsu Limited (Code: 6702) reported consolidated revenues of 4.0 trillion yen (US $36 billion) for the fiscal year ended March 31, 2019.

For more information, please see www.fujitsu.com.


Contact:
Fujitsu Laboratories Ltd.
Artificial Intelligence Laboratory
E-mail: [email protected]

Fujitsu Limited
Public and Investor Relations
Tel: +81-3-3215-5259
URL: www.fujitsu.com/global/news/contacts/
Source: Fujitsu Ltd
Sectors: AI

Copyright ©2019 JCN Newswire. All rights reserved. A division of Japan Corporate News Network.

Related Press Release


Fujitsu Successfully Grows Diamond Film to Boost Heat Dissipation Efficiency of GaN HEMT
December 05 2019 12:06 JST
 
Fujitsu Takes Key Step Toward Implementing SAP S/4HANA Manufacturing for Production Engineering and Operations to Streamline Aircraft Production at Kawasaki Heavy Industries
December 05 2019 10:11 JST
 
Fujitsu Begins Shipping Supercomputer Fugaku
December 02 2019 12:23 JST
 
Fujitsu Laboratories and Aichi Cancer Center in Japan Sign Comprehensive Joint Research Agreement to Drive Advances in Cancer Genomic Medicine with AI Technology
November 29 2019 10:17 JST
 
Fujitsu Formulates 'Fujitsu Future Insights - Digital Transformation in Retail'
November 27 2019 11:01 JST
 
Fujitsu Develops New "Actlyzer" AI Technology for Video-Based Behavioral Analysis
November 25 2019 17:47 JST
 
Fujitsu and RIKEN Claim 1st Place in the Green500 with Prototype of Fugaku Supercomputer
November 19 2019 08:06 JST
 
Fujitsu Launches "AuthConductor V2" to Take Biometric Authentication to the Next Level
November 18 2019 10:20 JST
 
Fujitsu Launches New PRIMEHPC Supercomputers Using Fugaku Technology
November 13 2019 09:37 JST
 
Cray and Fujitsu Partner to Power Supercomputing in the Exascale Era
November 13 2019 09:02 JST
 
More Press release >>

Latest Press Release


More Latest Release >>