Introducing A Solution For Hosting and Distributing Trained Deep Learning Models on Algorithmia …

By PR Newswire Article Rating: July 14, 2016 11:14 AM EDT   SEATTLE, July 14, 2016 /PRNewswire-iReach/ — Algorithmia, a Seattle-based startup building a serverless platform for algorithmic microservices, is excited to announce a solution for hosting and distributing trained deep learning models using GPUs in the cloud. Researchers and developers can now train their neural nets locally, and deploy them to Algorithmia’s scalable, cloud infrastructure, where they become smart API endpoints for other developers to use. Initial native support includes the Caffe, Theano, and TensorFlow deep learning frameworks, and 15 open source deep learning models, which run as microservices. Support for Torch and MxNet are coming soon.   Application developers can now obtain real-time predictions from deep learning models, and build production-ready apps using state-of-the-art machine intelligence in five-lines…


Link to Full Article: Introducing A Solution For Hosting and Distributing Trained Deep Learning Models on Algorithmia …

Pin It on Pinterest

Share This