Today we’re highlighting a method for training accurate #ML models for genetic discovery of diseases, even when using noisy and unreliable labels. Read how we applied this to better characterize lung function and chronic obstructive pulmonary disease ↓ https://
goo.gle/3LANzss
@googleai
-
Training ML Models for Genetic Disease Discovery with Noisy Labels
By
–
-
REMEDIS: Self-Supervised Learning Framework for Medical Imaging
By
–
Learn about REMEDIS, a unified large-scale self-supervised learning framework for building foundation medical imaging models that shows significant improvement in data-efficient generalization across medical imaging tasks and modalities. Check it out → https://t.co/65GL7hR6k0 pic.twitter.com/OJRgedDd0P
— Google AI (@GoogleAI) 26 avril 2023Learn about REMEDIS, a unified large-scale self-supervised learning framework for building foundation medical imaging models that shows significant improvement in data-efficient generalization across medical imaging tasks and modalities. Check it out → https://
goo.gle/41HmauE -
Trans Healthcare Technology Wins CHI 2023 Best Paper Award
By
–
Congratulations to the authors of "Infrastructuring Care: How Trans and Non-Binary People Meet Health and Well-Being Needs through Technology" for receiving the 2023 Best Paper Award from @acm_chi
! Learn more in the Mental Health and Care Work track today at 5:30pm at #CHI2023. -
LayerNAS Reframes Multi-Objective Neural Architecture Search Optimization
By
–
Introducing LayerNAS, an approach that reframes multi-objective neural architecture search within the framework of combinatorial optimization to greatly reduce search complexity, enabling more efficient discovery of high-performing models. Read more → https://t.co/BCn7MPLAsu pic.twitter.com/9J2xpPiHhU
— Google AI (@GoogleAI) 25 avril 2023Introducing LayerNAS, an approach that reframes multi-objective neural architecture search within the framework of combinatorial optimization to greatly reduce search complexity, enabling more efficient discovery of high-performing models. Read more → https://
goo.gle/3oJnGxP -
CHI 2023 Google Talks: UX Research and Student Opportunities
By
–
Today, check out one of our two #CHI2023 sponsor talks: "Transitioning from Academia to Industry: A UX Research Perspective" at 1:35pm and "Fellowships, Student Researchers, and Internships: How Students Can Engage with Google" at 7pm. See you there!
-
Google demos Rapsai Visual Blocks at CHI2023
By
–
Did you catch @michelleRcarney demo'ing Rapsai/Visual Blocks at the #CHI2023 Interactivity session last night? If not, drop by the Google booth at noon today to catch another live demo session. Learn more at https://
goo.gle/43VUwLK -
Google Researchers Showcase AI Projects at CHI2023
By
–
Attending #CHI2023 this year? Stop by the Google booth where you can chat with researchers and learn about some of the many projects Googlers are presenting throughout the conference. https://
goo.gle/40O6e8N -
Google’s Gil Shamir on Machine Learning Theory and Production
By
–
At the 2023 IEEE Information Theory Workshop (ITW-2023) this week, Google Research’s Gil Shamir will be giving a keynote presentation on “Machine Learning – From Theory to Production, or Is it From Production to Theory?” Learn more about it here:
-
Visual Blocks ML: Low-Code Framework for ML Pipeline Development
By
–
Introducing Visual Blocks ML, a low- to no-code framework that enables users to develop, test, and iterate on #ML pipelines. Learn how it can accelerate ML prototyping so users can launch multimedia applications in production faster → https://t.co/fojdnSQF4O pic.twitter.com/qe8X6fDHLe
— Google AI (@GoogleAI) 21 avril 2023Introducing Visual Blocks ML, a low- to no-code framework that enables users to develop, test, and iterate on #ML pipelines. Learn how it can accelerate ML prototyping so users can launch multimedia applications in production faster → https://
goo.gle/43VUwLK -
TiDE: Time-Series Dense Encoder for Long-Term Forecasting
By
–
Presenting TiDE, a time-series dense encoder for long-term time-series forecasting that enjoys the simplicity and speed of linear models while also being able to handle covariates and non-linear dependencies. Learn more →
https://
goo.gle/40GzWfT