This article provides an overview of applications where deep learning is used at the
network edge. Computer vision, natural language processing, network functions, and
virtual and augmented reality are discussed as example application drivers
[The Hardware Startup](https://knowen-production.s3.amazonaws.com/uploads/attachment/file/3754/Hardware%2Bas%2Bbusiness.pdf) by Renee DiResta , Brady Forrest , and Ryan Vinyard
[Hardware-as-a-Service](https://diff.substack.com/p/hardware-as-a-service?token=eyJ1c2VyX2lkIjoxMjA3OTgxNywicG9zdF9pZCI6MTYxNTc5NzQsIl8iOiJaSkdBRyIsImlhdCI6MTYwNDA3NTgxNywiZXhwIjoxNjA0MDc5NDE3LCJpc3MiOiJwdWItMTk0MzAiLCJzdWIiOiJwb3N0LXJlYWN0aW9uIn0.J0TBzTy6xj5t47pKdE-x5uCqrW-tX4TQCLJDwVwrJ1w) by Byrne Hobart from The Diff
> Paul Graham points out something Fitbit, GoPro, and Sonos investors have also observed: hardware is hard.
## Hardware is hard
## +++ [Energy Efficient Computing Systems: Architectures, Abstractions and Modeling to Techniques and Standards](https://arxiv.org/pdf/2007.09976.pdf) RAJEEV MURALIDHAR, The University of Melbourne and Amazon Web Services
## tinyML - [next AI revolution](https://knowen-production.s3.amazonaws.com/uploads/attachment/file/5122/Untitled%2B45.pdf)
- [deep learning with edge](https://www.cs.ucr.edu/~jiasi/pub/deep_edge_review.pdf)
> This article provides an overview of applications where deep learning is used at the
> network edge. Computer vision, natural language processing, network functions, and
> virtual and augmented reality are discussed as example application drivers
## +++ [tinyML for ubiquitous AI computing - review](https://arxiv.org/ftp/arxiv/papers/2102/2102.01255.pdf)
**the picture of the stages - Cloud ML, mobile ML, tinyML**
