Google today introduced AdaNet, an open source tool for combining machine learning algorithms to achieve better predictive insights. AdaNet is available today on the Tensor GitHub repository.
“AdaNet builds on our recent reinforcement learning and evolutionary-based AutoML efforts to be fast and flexible while providing learning guarantees,” Google AI software engineer Charles Weill said in a blog post. “Importantly, AdaNet provides a general framework for not only learning a neural network architecture, but also for learning to ensemble to obtain even better models.”
Disclaimer: This section is a compilation of news, articles, updates and information (“Updates”) related to payments,fintech, banking and other industry. All Updates belong to the source provided after every such Update. FIAKS does not have and in no manner claims to have any intellectual property rights in the content, images, pdf, videos etc. in any of the Updates. This section has been created for knowledge sharing/education purposes for our smart FIAKS communities across the globe. We understand that the fair use of a copyrighted work or work protected under any intellectual property law, including such use by reproduction in copies or by any other means specified under applicable laws, for purposes such as criticism, comment, news reporting, teaching (including multiple copies for classroom use), scholarship, or research, is not an infringement of copyright. This section and our website may contain certain copyrighted or the work otherwise protected under any law that were not specifically authorised to be used by the copyright holder(s) or right holder(s) but which we believe in good faith are protected by the applicable laws and the fair use doctrine for one or more reasons noted above. If you have any specific concerns about this section or our website or our position on the fair use defence, please contact us at contactus@fiaks.com so we can discuss amicably. Thank you.