Where to get help
How to improve a draft
You can also browse Wikipedia:Featured articles and Wikipedia:Good articles to find examples of Wikipedia's best writing on topics similar to your proposed article. Improving your odds of a speedy review To improve your odds of a faster review, tag your draft with relevant WikiProject tags using the button below. This will let reviewers know a new draft has been submitted in their area of interest. For instance, if you wrote about a female astronomer, you would want to add the Biography, Astronomy, and Women scientists tags. Editor resources
|  |
 | This article provides insufficient context for those unfamiliar with the subject. (2023) |
| Real-time Artificial Neural Tool (RANT) | |
|---|---|
| Original author | Douglas Santry |
| Release | 2023 |
| Operating system | Linux,[1] Mac OS,[1] Microsoft Windows[1] |
| Type | |
| License | BSD License 2.0 |
| Website | github |
RANT is Deep Learning library written in C++, with Python (programming language) bindings. The library addresses real-time deep learning applications. There are many deep learning libraries and frameworks available for Python; there is rich deep learning ecosystem. Real-time systems tend to have few resources, and bounded compute times. Many applications, such as embedded systems do not support running Python. RANT is written in C++. It can be used to build light-weight C++ applications, or it can be used in Python with RANT's Python bindings.
RANT is written in C++ and compared to Python frameworks experimentally. RANT typically requires only 10's of megabytes of memory, instead of gigabytes. The library also offers predictable inference latencies that are orders of magnitude smaller than python, as are the means and standard deviations [2].
At around 10,000 lines of code the library is extremely extensible and adaptable.
History
editRANT was written in support of the book, Demystifying Deep Learning, published by Wiley and the IEEE Press (ISBN 978-1-394-20562-2). It demonstrates the principles involved in designing and implementing a deep learning library. The focus is CPU oriented, as opposed to distributed systems of GPUs. By targeting embedded and real-time systems the modest resource demands make it easy for students to experiment. The assumption of a CPU lends itself to pedagogical use as students have access to CPUs on their laptops.
- provide significant coverage: discuss the subject in detail, not just brief mentions or routine announcements;
- are reliable: from reputable outlets with editorial oversight;
- are independent: not connected to the subject, such as interviews, press releases, the subject's own website, or sponsored content.
Please add references that meet all three of these criteria. If none exist, the subject is not yet suitable for Wikipedia.