File	Date	Author	Commit
docs	2015-05-03	slpnght@gmail.com	[79845b] disabled badly working ultradeep in random search
lib	2015-05-05	cutesolar	[d34cca] better handling of variance of estimates
missing_headers	2014-11-17	slpnght@gmail.com	[6ccc29] importing 0.5.1 version source code into reposi...
src	2016-11-10	Tomas Ukkonen	[907c0d] Backported nnetwork code bugfix (maxwidth was i...
tools	2015-05-05	cutesolar	[afda0f]
AUTHORS	2020-04-08	Tomas Ukkonen	[9350ec] authors update
KNOWN_BUGS	2014-11-24	slpnght@gmail.com	[fc0460] fixed some threading issues in BFGS/LBFGS code ...
LICENSE	2017-05-12	Tomas Ukkonen	[1f6220] Update LICENSE
Makefile.in	2014-11-17	slpnght@gmail.com	[20a834] needed unwise message
README	2017-05-05	Tomas Ukkonen	[ea05b2] Update README
blastest.c	2014-11-27	slpnght@gmail.com	[472fa4] openblas is now detected/used. vertex/matrix al...
build.sh	2014-11-17	slpnght@gmail.com	[6ccc29] importing 0.5.1 version source code into reposi...
config.h	2014-11-28	slpnght@gmail.com	[45c4c5] removed unneeded openblas flag detections from ...
config.h.in	2014-11-17	slpnght@gmail.com	[6ccc29] importing 0.5.1 version source code into reposi...
configure	2014-11-30	slpnght@gmail.com	[648fd5] doc updates
configure.ac	2014-11-30	slpnght@gmail.com	[648fd5] doc updates
copy_cpp_templates.sh	2014-11-17	slpnght@gmail.com	[6ccc29] importing 0.5.1 version source code into reposi...
cputest.c	2014-11-17	slpnght@gmail.com	[6ccc29] importing 0.5.1 version source code into reposi...
dinrhiw.pc.in	2014-11-27	slpnght@gmail.com	[472fa4] openblas is now detected/used. vertex/matrix al...
gmptest.c	2014-11-17	slpnght@gmail.com	[6ccc29] importing 0.5.1 version source code into reposi...
install-sh	2014-12-08	slpnght@gmail.com	[d2351e] initial change for ica-basis regularization cod...
openblastest.c	2014-11-27	slpnght@gmail.com	[472fa4] openblas is now detected/used. vertex/matrix al...
zlibtest.c	2014-11-17	slpnght@gmail.com	[6ccc29] importing 0.5.1 version source code into reposi...

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      outdated and contains bugs.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>