Search
Code Directory
 ASP
 ASP.NET
 C/C++
 CFML
 CGI/PERL
 Delphi
 Development
 Flash
 HTML
 Java
 JavaScript
 Pascal
 PHP
 Python
 SQL
 Tools
 Visual Basic & VB.NET
 XML
New Code
Easy CSS Menu 5.0
Bytescout PDF SDK 1.7.0.222
Kickstarter clone script 2.0.5
Indiegogo Clone 3.0
Mercato 1.0
Readymade PHP Classified Script 3.3
Udacity Clone Script 1.20
PHP News Script 1.0.5
Exe Guarder 4.14
dbForge Search 2.2
EaseClouds Virtual File System SDK 2.1.1.2
dbForge SQL Decryptor 3.1
Fortune Gigs Script 2.03
Pricing Plans and Subscription Payment Script 1.0
PHP Image Resize Script 1.0
Top Code
Easy CSS Menu 5.0
Billing System 1.0.1
PHP Image Resize Script 1.0
Image Edge Detection Using Ant Colony Optimization 1.0
Matlab Face Detection using classifiers and adaptive boosting 1.0
Chatbot widget 1.0.0
Udacity Clone Script 1.20
dbForge Search 2.2
Best Spotify Clone 1.0
CONVOLUTION IN MATLAB WITHOUT USING conv(x,h) 1.0
ASIO Proxy
JDrawingPanel 0.1
Javast 1.0
PHP News Script 1.0
Java-2-Pseudo 1.0
Top Rated
PHP Image Resize Script 1.0
Jango Clone Script 1.0
Best Spotify Clone 1.0
Get Random Record Based on Weight 1.0.0
Travel Portal Script 9.29
Magento Product Designer 1.0
OFOS - Just Eat Clone Script 1.0
PrestaShop Upload Images Module 1.2.1
Trading Software 1.2.4
ADO.NET Provider for ExactTarget 1.0
Solid File System OS edition 5.1
Classified Ad Lister 1.0
Aglowsoft SQL Query Tools 8.2
Sine Wave Using JavaFX 1.0
ICPennyBid Penny Auction Script 4.0
CNN - Convolutional neural network class 1.0
File ID: 78858






CNN - Convolutional neural network class 1.0
Download CNN - Convolutional neural network class 1.0http://www.mathworks.comReport Error Link
License: Freeware
File Size: 1.3 MB
Downloads: 223
Submit Rating:
CNN - Convolutional neural network class 1.0 Description
Description: This project provides matlab class for implementation of convolutional neural networks. This networks was developed by Yann LeCun and have sucessfully used in many practical applications, such as handwritten digits recognition, face detection, robot navigation and others (see references for more info). Because of some architectural features of convolutional networks, such as weight sharing it is imposible to implement it using Matlab Neural Network Toolbox without it's source modifications. That's why this class works almost independently from NN toolbox (coming soon full independence).

This release includes sample of handwritten digits recognition using CNN. If you just want to try it run cnet_tool. You'll see a simple GUI. It loads pretrained convolutional neural net from cnet.mat and recognizes image of digit either painted in painting area or downloaded from MNIST database.

The significant improovement in this version is support of nVidia CUDA technology, which speeds up the training up to 44 times. You'll need a CUDA-capable graphic card and CUDA SDK (especially cudart.dll and cublas.dll). Currently only stochastic gradient is supported by CUDA-training, but Hessian approximation is going to be soon also.
IMPORTANT:since matlabcentral is not allows to include mex-files into submission, you need to download cudacnn.mex (mex32 or mex64) from https://sites.google.com/site/mihailsiroten...l-network-class for full functionality.
Though without cudacnn.mex this software is also functional in usual way.
To run CUDA-based training use cutrain_cnn.m
Note that ther're some problems with CUDA v3.
The source of cudacnn.mex is not included by now, but I plan to do It in future.
See readme.txt for more details.
Changes in version 0.81:
- Compatibility with Matlab 2010 issue fixed (Thanks to Silvio Filipe)

License: Freeware

Related: stochastic, Gradient, cublasdll, cudartdll, supported, cudatraining, alsoimportantsince, matlabcentral, approximation, hessian, Graphic, cudacapable, improovement, Version, significant, databasethe, downloaded

O/S:BSD, Linux, Solaris, Mac OS X

File Size: 1.3 MB

Downloads: 223



More Similar Code

RubyFann Bindings to use FANN (Fast Artificial Neural Network) from within ruby/rails environment. Requires: Ruby 1.8.6 or greater. gnu make tools or equiv for native code in ext To install: sudo gem install ruby-fann



Generic Neural Network. It's a class to build almost any type of Neural Networks, from a simple Perceptron to a SOM, supporting recurrence.



The form of a single layer feed forward neural network lends itself to finding the gradient. This is useful when the network is used for surrogate optimization or other algorithms that use gradients. Requires creating a file by modifying a NN...



This little package contains a Parzen Neural Network classifier that can classify data between N classes in D dimensions. The classifier is really fast and simple to learn. The good classification performance can be obtained for a certain class of...



this model show the design of sun seeker control system using neural network model refrence with neural network toolbox and SIMULINK with MATLAB



Multilayer Perceptron Neural Network Model and Backpropagation Algorithm for Simulink.
Multilayer Perceptron Neural Network Model and Backpropagation Algorithm for Simulink.

Marcelo Augusto Costa Fernandes
DCA - CT - UFRN



A Ruby extension that provides a 2-Layer Back Propagation Neural Network, which can be used to categorize datasets of arbitrary size. The network can be easily (re-)stored to/from the hard disk.



SFAM is an incremental neural network classifier. It is a simple and fast version of Fuzzy ARTMAP (FAM). Both FAM and SFAM produce the same output given the same input.

References:
[1] Kasuba, T. (1993). "Simplified fuzzy...



This package includes files for modelling nonlinear dynamic systems using a recurrent generalized neural network. The learning scheme uses the complex method of nonlinear nonderivative optimization, thereby avoiding the problems of computing the...



Simple Matlab Code for Neural Network Hebb Learning Rule.
It is good for NN beginners students. It can be applied for simple tasks e.g. Logic "and", "or", "not" and simple images classification.

User Review for CNN - Convolutional neural network class
- required fields
     

Please enter text on the image