The rust autograd package is a port of tensorflow and pytorch facilities to rust. I am still familiarizing myself with the project, so I am writing down all the calculus rules used so I can understand the math a little bit better:

f(x) | f'(x) |
---|---|

sin(g(x)) | g'(x)*cos(g(x)) |

cos(g(x)) | g'(x)*-sin(g(x)) |

abs(g(x)) | g(x)*g'(x)/abs(g(x)) |

c*g(x) | c*g'(x) |

-g(x) | -g'(x) |

g(x)^c | c*(g(x)^(c-1))*g'(x) |

g(x)^2 | 2*g(x)*g'(x) |

g(x)^-1 | -g'(x)/(g(x)^2) |

sqrt(g(x)) | g'(x)/2*sqrt(g(x)) |

- Google Search
- DuckDuckGo Search
- Sogou Search
- Bing Search
- Baidu Search

- Rust Procedural Macro Spans Quirks Mode and Hygiene
- Tokenizing and Stemming Natural Language in Rust
- Text to Speech Software in Rust
- Generating an Atom Feed for a site written in RDXL
- Navigating the Rust RFC Process and Agile Development
- Interfacing C Variadic Functions in Rust
- Rust Zeroize to Protect Hot Secrets
- A Short List of Rust Libraries that I Recommend
- Complex Pattern Guards in Rust
- Generating Lots of Misspelled Words for NLP Testing
- Dependency Grammar vs Constituency Grammars
- Using rust-bert to Summarize Blog Posts
- Rust, typed: traits and trait objects
- Rust, shared: by copy
- Rust, abstracted: lambda dropping