-
Notifications
You must be signed in to change notification settings - Fork 12
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Added README files for the ANNT library.
- Loading branch information
1 parent
aebc3af
commit ebd7288
Showing
1 changed file
with
20 additions
and
1 deletion.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,3 +1,22 @@ | ||
 | ||
# ANNT | ||
Work in progress ... To be described soon. | ||
|
||
ANNT is a lightweight C++ library implementing some of the common architectures of artificial neural networks: | ||
* Fully connected; | ||
* Convolutional; | ||
* Simple recurrent networks (RNN), Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU). | ||
|
||
The library comes with a number of sample applications, which demonstrate its usage in solving different tasks. The provided samples cover all of the implemented neural network architectures. | ||
|
||
## Building the code | ||
|
||
The code comes with MSVC solution files ([src/make/msvc](src/make/msvc)) and GCC make file ([src/make/gcc](src/make/gcc)). On Windows, simply open solution file in MS Visual Studio and hit build. On Linux just use "make" command to build the library. In both cases the built library ends up in the "/build/compiler/mode" folder, which also contains the necessary header files. | ||
|
||
## Additional reading | ||
|
||
The ANNT library and some of the theory about artificial neural networks is described in a set of articles published on Code Project: | ||
* [Feed forward fully connected neural networks](https://www.codeproject.com/Articles/1261763/ANNT-Feed-forward-fully-connected-neural-networks); | ||
* [Convolutional neural networks](https://www.codeproject.com/Articles/1264962/ANNT-Convolutional-neural-networks); | ||
* [Recurrent neural networks](https://www.codeproject.com/Articles/1272354/ANNT-Recurrent-neural-networks). | ||
|
||
|