dinrhiw2 (copy of main repo from github) Code
Dinrhiw2 - machine learning library and tools (neural networks) in C++
Brought to you by:
cutesolar
Menu
▾
▴
Tree [1f6220] master / History
slpnght@gmail.com
Read Me
WHAT DINRHIW2 IS?
-----------------
Primary aim of the dinrhiw is to be linear algebra library and machine learning
library. For this reason dinrhiw implements PCA and neural
network codes. Currently, the neural network code only supports:
* hamiltonian monte carlo sampling (HMC) and simple bayesian neural network
* second order L-BFGS search
* gradient descent (backpropagation)
NOTE: please use experimental branch (RBM_test) as stable branch is seriously
outdated and contains bugs. RBM_test contains experimental RBM weight
pretraining/deep learning code (not fully working atm) and experimental
reinforcement learning code (currently cannot learn well from data).
Read wiki pages for further documentation: https://github.com/cslr/dinrhiw2/wiki
BUILDING IT
-----------
To build and install library execute
./build.sh
make install
commands at the top level.
For the working examples how to use dinrhiw look at the tools directory
below the root dictory.
Building it (tst after installing the library) creates three programs:
aescipher - shows how to use AES encryption module.
dstool and nntool - dataset management and neural network weight learning.
So the keyfiles to read for the (neural network) documentation are
tools/nntool.cpp
src/dataset.h
src/neuralnetwork/nnetwork.h
==============================================================================
Additionally, there are
tools/test_data.sh
tools/test_data2.sh
tools/test_data3.sh
ADDITIONAL NOTES
----------------
The library contains needless implementation of various algorithms
that DO NOT belong to this library. They will be removed slowly
before 1.0 release. (cleanup the code)
Tomas Ukkonen <tomas.ukkonen@iki.fi>
