Pages

▼
Showing posts with label Conditional Restricted Boltzmann Machine. Show all posts
Showing posts with label Conditional Restricted Boltzmann Machine. Show all posts
Saturday, 3 September 2016

Possible Addition of NARX Network to Conditional Restricted Boltzmann Machine

›
It has been over three months since my last post , due to working away from home for some of the summer, a summer holiday and moving home. H...
Wednesday, 3 February 2016

Refactored Denoising Autoencoder Update #2

›
Below is this second code update. % select rolling window length to use - an optimisable parameter via pso? rolling_window_length = 50 ; b...
Thursday, 21 January 2016

Refactored Denoising Autoencoder Code Update

›
This code box contains updated code from my previous post . The main change is the inclusion of bias units for the directed auto-regressive ...
Monday, 18 January 2016

Refactored Denoising Autoencoder Code

›
It has been quite a challenge but I now have a working first attempt at  Octave code for autoencoder pre-training of weights for a  Conditi...
Friday, 25 September 2015

Runge-Kutta Methods

›
As stated in my previous post I have been focusing on getting some meaningful features as possible inputs to my machine learning based trad...
Thursday, 23 April 2015

A Simple Visual Test of CRBM Performance

›
Following on from the successful C++ .oct coding of the Gaussian and Binary units, I thought I would conduct a simple visual test of the con...
1 comment:
Monday, 20 April 2015

Optimised CRBM Code for Binary Units

›
Following on from my previous post, in the code box below there is the C++ .oct code for training the binary units of the CRBM and, as with ...
Thursday, 16 April 2015

Optimised CRBM Code for Gaussian Units

›
Over the last few weeks I have been working on optimising the conditional restricted boltzmann machine code, with a view to speeding it up ...