Comments on: Update 3.4 Released http://blog.peltarion.com/2006/05/27/update-34-released/ The Peltarion Blog Fri, 25 Jun 2010 11:27:30 +0000 http://wordpress.org/?v=2.9.2 hourly 1 By: Thomas (Peltarion) http://blog.peltarion.com/2006/05/27/update-34-released/comment-page-1/#comment-58 Thomas (Peltarion) Thu, 20 Jul 2006 07:00:57 +0000 http://blog.peltarion.com/2006/05/27/update-34-released/#comment-58 Hi, You can use Levenberg-Marquardt as well with components that support gradient optimization. As for network pruning, that's what the optimizers are for (GA, particle swarm etc). There are also implicit pruning methods through unsupervised training (weight decay...). As for sensitivity analysis, while you can use it for pruning purposes, it is something that I would not recommend. The sensitivity approach is simply a too blunt instrument as it doesn't take into consideration the complexities of the non-linearity of the systems and the correlation of data. In most cases it will do more damage than it will help. The best pruning approach is through the use of global optimizers that optimize the whole system topology. --Thomas Hi,

You can use Levenberg-Marquardt as well with components that support gradient optimization. As for network pruning, that’s what the optimizers are for (GA, particle swarm etc). There are also implicit pruning methods through unsupervised training (weight decay…).

As for sensitivity analysis, while you can use it for pruning purposes, it is something that I would not recommend. The sensitivity approach is simply a too blunt instrument as it doesn’t take into consideration the complexities of the non-linearity of the systems and the correlation of data. In most cases it will do more damage than it will help.

The best pruning approach is through the use of global optimizers that optimize the whole system topology.

–Thomas

]]> By: SAndhya Samarasinghe http://blog.peltarion.com/2006/05/27/update-34-released/comment-page-1/#comment-57 SAndhya Samarasinghe Thu, 20 Jul 2006 04:39:14 +0000 http://blog.peltarion.com/2006/05/27/update-34-released/#comment-57 Hi I am also wondering if you do now or plan to use sensitivity approaches to network pruning in MLP to optimize the networks as this approach may be more useful in deleting links more meaningfully and methodically? Hi
I am also wondering if you do now or plan to use sensitivity approaches to network pruning in MLP to optimize the networks as this approach may be more useful in deleting links more meaningfully and methodically?

]]> By: SAndhya Samarasinghe http://blog.peltarion.com/2006/05/27/update-34-released/comment-page-1/#comment-56 SAndhya Samarasinghe Thu, 20 Jul 2006 04:32:49 +0000 http://blog.peltarion.com/2006/05/27/update-34-released/#comment-56 Hi I am wondering if you use any other second order error minimization methods than QuickPRop. I mean Levenberg Marquardt, Conjugate Gradient, Newton method etc. in MLP. Hi
I am wondering if you use any other second order error minimization methods than QuickPRop. I mean Levenberg Marquardt, Conjugate Gradient, Newton method etc. in MLP.

]]> By: Robert http://blog.peltarion.com/2006/05/27/update-34-released/comment-page-1/#comment-13 Robert Wed, 31 May 2006 01:15:43 +0000 http://blog.peltarion.com/2006/05/27/update-34-released/#comment-13 I had some trouble installing it until I realized that my firewall was blocking it out. Doh! I had some trouble installing it until I realized that my firewall was blocking it out. Doh!

]]> By: Zeppo http://blog.peltarion.com/2006/05/27/update-34-released/comment-page-1/#comment-12 Zeppo Sun, 28 May 2006 23:53:38 +0000 http://blog.peltarion.com/2006/05/27/update-34-released/#comment-12 Good work, the csv file format is much bettern now. Thanks. Good work, the csv file format is much bettern now. Thanks.

]]>