CONNECT WITH US:
Feb, 13 2018 12:50 JST
Appier Demonstrates Breakthrough in Creativity in Artificial Intelligence
Pioneering study takes a unique approach to applying cutting edge deep learning technology to apparel design
TAIPEI, TAIWAN, Feb, 13 2018 - (Media OutReach) - Appier, a leading artificial intelligence (AI) company, demonstrated pioneering research that showcased AI's ability to be creative at the 32nd AAAI Conference on Artificial Intelligence (AAAI-18), one of the world's leading conferences in AI. AI's ability to create and design items that humans will find appealing is considered the next important breakthrough in the field - and Appier's research suggests that the day when AI can help designers in their day-to-day work might be closer than we thought.
The Appier team, comprising Yong-Siang Shih, Dr. Kai-Yueh Chang and Dr. Hsuan-Tien Lin from Appier and Prof. Min Sun from National Tsing Hua University, designed an AI model that first mimics the human ability to put together and design outfits, after observing and learning from examples of good design. They did this with deep learning techniques in combination with a new Projected Compatibility Distance (PCD) methodology which they designed, that discerns the distance between compatible items.
This compatibility distance is then used to run through a unique application of Generative Adversarial Networks (GANs) to generate novel compatible apparel items when apparel images are input. The output results capture the designers' concept of how different apparel items combine with one another and is then used to create new apparel designs.
"This is an exciting step forward towards realizing creativity in AI. Appier's vision has always been for AI to help humans in all aspects of life, and this includes creativity. We don't however, see AI replacing human creativity, just amplifying it," said Chih-Han Yu, co-founder and CEO, Appier. "At Appier, we are always striving to close the gap between academic AI and the business world and this pioneering work by our employees is one example of the various innovation projects that we've adopted to achieve this."
"The team chose apparel design to apply our model because of the inherent complexity and subjectivity in matching different outfits as well as the potential for application in the business world. We also wanted to show the potential for creativity in AI using our unique applications of deep learning techniques in compatibility distance and GAN. The designs generated by our model easily passed the human test which has given us tremendous encouragement," said Dr. Hsuan-Tien Lin, Chief Data Scientist, Appier.
The paper, entitled "Compatibility Family Learning for Item Recommendation and Generation", can be viewed in its entirety here.
Appier is a technology company which aims to provide artificial intelligence (AI) platforms to help enterprises solve their most challenging business problems. For more information please visit www.appier.com.
For media enquiries, please contact
Copyright ©2018 JCN Newswire. All rights reserved. A division of Japan Corporate News Network.
DENSO Leads Dellfer's Initial Funding Round, Supporting Cybersecurity for Connected Vehicles
Feb 22, 2018 15:22 JST
NEC Uses AI to Optimize Inventory and Maintenance with Highly Precise Predictions
Feb 22, 2018 15:05 JST
Denso: European Commission's Announcement Concerning the EU Competition Law related to Certain Automotive Components
Feb 21, 2018 20:37 JST
MITSUBISHI e-EVOLUTION CONCEPT European Premiere and New 2019 Model Year Outlander PHEV Global Premiere
Feb 21, 2018 13:27 JST
Fujitsu to Provide Customer Contact Point Platform to Shizuoka Bank for the Realization of Digital Banking Services
Feb 21, 2018 12:53 JST
Fujitsu Group Environmental Report 2017 Wins the Grand Award of Global Warming Countermeasures Report (Japanese Environment Minister's Award)
Feb 21, 2018 12:23 JST
Eisai Certified in 2018 as Outstanding Health and Productivity Management Organization (White 500)
Feb 21, 2018 09:25 JST
Hitachi and Hitachi Asia (Thailand) Sign MoU with Thailand Post to Support the Digitization of Postal Services
Feb 20, 2018 21:28 JST
Lexus at the 2018 Geneva Motor Show
Feb 20, 2018 21:23 JST
Toyota Develops New Magnet for Electric Motors Aiming to Reduce Use of Critical Rare-Earth Element by up to 50%
Feb 20, 2018 20:06 JST
Fujitsu Commences Sales of IoT Service Platform "SMAVIA," Accelerating Digital Transformation in Retail and Distribution
Feb 20, 2018 10:46 JST
MHI Thermal Systems to Launch 19 Room Air-Conditioner Models into the Domestic Market
Feb 19, 2018 11:32 JST
NEC Contributes to Ecosystem for Enhancing Virtualized Network Orchestration
Feb 19, 2018 11:08 JST
DOCOMO to Showcase Future of 5G Entertainment, Transportation, Construction and Environment at Mobile World Congress 2018
Feb 16, 2018 16:09 JST
Fujitsu Launches Biometric Authentication Software "AuthConductor Client" for PCs
Feb 16, 2018 11:03 JST
Eisai: U.K. NICE Recommends Anticancer Agent Lenvima as Treatment for Thyroid Cancer
Feb 16, 2018 08:34 JST
DOCOMO Tightens Security for Open APIs by Leveraging Know-how of Affiliate Authlete, Inc.
Feb 15, 2018 15:59 JST
Showa Denko (SDK) Announces Difference between Performance Forecast and Results, Posting of Extraordinary Loss, and Revision of Dividend Forecast
Feb 14, 2018 17:30 JST
Showa Denko (SDK) Announces 2017 Consolidated Financial Results
Feb 14, 2018 17:00 JST
NEC Develops Low-power Consumption Circuit Technologies for Compact Millimeter-Wave Radio Units
Feb 14, 2018 13:54 JST
More Latest Release >>
Appier demonstrates AI's ability to recommend matching clothes and create beautiful apparel designs at AAAI 2018.
Appier Named in CB Insights' Second Annual AI 100 Companies
December 19 2017 08:00 JST
Appier Demonstrates Efficacy of Artificial Intelligence in Fighting Ad Fraud
December 12 2017 10:00 JST
More Press release >>