[행사/세미나] 해외전문가 초청 세미나 (9.16 월 10:30~)
- 인공지능학과
- 조회수24315
- 2019-09-09
일시: 2019.09.16(월) 10:30~12:00
장소: 반도체관 400126호
연사: Prof. Tsachy Weissman (Stanford University)
Title: "What machines can learn from humans about compression"
Abstract:
Inspired by Shannon's work on estimating the entropy of a language, we experimented with a framework for image compression comprising one human describing images using text instructions to another, who is tasked with reconstructing the original image. These image reconstructions were then rated by human scorers on the Amazon Mechanical Turk platform and compared to reconstructions obtained by existing image compressors. We've conducted similar experiments for audio compression. The insights gleaned offer a perspective on the potential for substantial improvements over current approaches to lossy compression and related information processing tasks. Related reading:
https://arxiv.org/abs/1810.11137and https://theinformaticists.com/2019/09/05/journal-for-high-schoolers-in-2019/
Bio:
Tsachy Weissman has been on the faculty of the Electrical Engineering department at Stanford since 2003, where he enjoys activities such as research and teaching the science of information. He has served and still does on editorial boards for scientific journals, technical advisory boards in industry, and as founding director of the Stanford Compression Forum. His favorite gig to date was being an advisor to the HBO show “Silicon Valley” until he was terminated when it was realized his students are more creative and reliable consultants. He hates writing about himself in the third person.
Abstract:
Inspired by Shannon's work on estimating the entropy of a language, we experimented with a framework for image compression comprising one human describing images using text instructions to another, who is tasked with reconstructing the original image. These image reconstructions were then rated by human scorers on the Amazon Mechanical Turk platform and compared to reconstructions obtained by existing image compressors. We've conducted similar experiments for audio compression. The insights gleaned offer a perspective on the potential for substantial improvements over current approaches to lossy compression and related information processing tasks. Related reading:
https://arxiv.org/abs/1810.11137and https://theinformaticists.com/2019/09/05/journal-for-high-schoolers-in-2019/
Bio:
Tsachy Weissman has been on the faculty of the Electrical Engineering department at Stanford since 2003, where he enjoys activities such as research and teaching the science of information. He has served and still does on editorial boards for scientific journals, technical advisory boards in industry, and as founding director of the Stanford Compression Forum. His favorite gig to date was being an advisor to the HBO show “Silicon Valley” until he was terminated when it was realized his students are more creative and reliable consultants. He hates writing about himself in the third person.