Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Automatic Differentiation Library for Computational and Mathematical Engineering
| Date | Stars |
|---|---|
| 2026-07-24 | 319 |
| 2026-07-25 | 319 |
| 2026-07-28 | 319 |
| 2026-07-30 | 319 |
| 2026-08-06 | 319 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<p align="center"> <img src="https://github.com/ADCMEMarket/ADCMEImages/blob/master/ADCME/ADCME.gif?raw=true" alt="ADCME"/> </p>     The ADCME library (**A**utomatic **D**ifferentiation Library for **C**omputational and **M**athematical **E**ngineering) aims at general and scalable inverse modeling in scientific computing with gradient-based optimization techniques. It is built on the deep learning framework, **graph-mode [TensorFlow](https://www.tensorflow.org/)**, which provides the automatic differentiation and parallel computing backend. The dataflow model adopted by the framework makes it suitable for high performance computing and inverse modeling in scientific computing. The design principles and methodologies are summarized in the [slides](https://kailaix.github.io/ADCMESlides/ADCME.pdf). Check out more about [slides and videos on ADCME](https://kailaix.github.io/ADCME.jl/dev/videos_and_slides/)! | [Install ADCME and Get Started (Windows, Mac, and Linux)](https://www.youtube.com/playlist?list=PLKBz8ohiA3IlrCI0VO4cRYZp2S6SYG1Ww) | [Scientific Machine Learning for Inverse Modeling](https://www.youtube.com/playlist?list=PLKBz8ohiA3In-ZlvBKbvj_TIQEaboGC9_) | [Solving Inverse Modeling Problems with ADCME](https://www.youtube.com/playlist?list=PLKBz8ohiA3ImaNykOv56ONnCofEQMg3B8) | ...**more** on [ADCME Youtube Channel](https://www.youtube.com/channel/UCeaZFluNatYpkIYcq2TTklw/playlists)! | | ------------------------------------------------------------ | ------------------------------------------------------------ | ------------------------------------------------------------ | ------------------------------------------------------------ | | [](https://www.youtube.com/playlist?list=PLKBz8ohiA3IlrCI0VO4cRYZp2S6SYG1Ww) | [](https://www.youtube.com/playlist?list=PLKBz8ohiA3In-ZlvBKbvj_TIQEaboGC9_) | [](https://www.youtube.com/playlist?list=PLKBz8ohiA3ImaNykOv56ONnCofEQMg3B8) | [](https://www.youtube.com/channel/UCeaZFluNatYpkIYcq2TTklw/playlists) | Several features of the library are * **MATLAB-style Syntax**. Write `A*B` for matrix production instead of `tf.matmul(A,B)`. * **Custom Operators**. Implement operators in C/C++ for performance critical parts; incorporate legacy code or specially designed C/C++ code in `ADCME`; automatic differentiation through implicit schemes and iterative solvers. * **Numerical Scheme**. Easy to implement numerical schemes for solving PDEs. * **Physics Constrained Learning**. Embed neural network into PDEs and solve with any numerical schemes, including implicit and iterative schemes. * **Static Graphs**. Compilation time computational graph optimization; automatic parallelism for your simulation codes. * **Parallel Computing**. [Concurrent execution](https://kailaix.github.io/ADCME.jl/dev/multithreading/) and model/data parallel [distributed optimization](https://kailaix.github.io/ADCME.jl/dev/mpi/). * **Custom Optimizers**. Large scale constrained optimization? Use `CustomOptimizer` to integrate your favorite optimizer. Try out prebuilt [Ipopt and NLopt](https://kailaix.github.io/ADCME.jl/dev/customopt/#Dropin-substitute-of-BFGS!-1) optimizers. * **Sparse Linear Algebra**. Sparse linear algebra library tailored for scientific computing. * **Inverse Modeling**. Many inverse modeling algorithms have been developed and impleme
Excerpt of 17,910 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:3fe64edf3f5aeb22, topic:tensorflow, readme:deep learning framework, desc:automatic differentiation
matched fp:3fe64edf3f5aeb22, topic:scientific-computing