[Top][All Lists]

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [Gneuralnetwork] New Feature: bayesian network

From: Aljosha Papsch
Subject: Re: [Gneuralnetwork] New Feature: bayesian network
Date: Mon, 16 May 2016 19:53:14 +0200
User-agent: Mozilla/5.0 (X11; Linux x86_64; rv:38.0) Gecko/20100101 Icedove/38.7.2

Hi Tobias,

On 09.05.2016 12:05, Tobias Wessels wrote:
Dear Gneural Network community,

I have worked quite some time on the library now, and I have researched
the feasibility of a new algorithm to train the network and calculate
output statistics based on bayesian statistics. It works well with both
curve fitting tests, although it is still quite slow. However, it can be
easily parallelized, so it is to be expected that improvements are still

Unfortunately, due to the intransparent development and the huge change
in the codebase (I had to write a whole new framework for this feature),
I have developed a fork of version 0.8 and I have not ported it back to
gneural network yet. However, I would like to share my findings with
you. For that, I have set up a GitHub repository , which you can access
at and I would be happy if you
give your comments and ideas regarding this feature. Please also read
the file in that git repository.
If you are interested, I am willing to port this back into the gneural
network codebase, but first I'll invite you to play with this piece of
The intransparent development is a weakness that I hope will be improved soon. It is currently being worked upon to make the Git repository on Savannah the primary means of development. It's not ready because the Git repository only stores release snapshots, so it will be revamped on the current work and hopefully all developers will use Git. Once the repo is ready your patches are most likely welcome to be included. Unfortunately I'm not involved in the science and can't comment on that. Others will have to do that.

reply via email to

[Prev in Thread] Current Thread [Next in Thread]