Rank: 625 based on 115 downloads (last 30 days) and 1 file submitted

Mihail Sirotenko

E-mail: mihail.sirotenko@gmail.com
Company/University: Southern Federal University
Lat/Long: 47.13999938964844, 38.54000091552734

Personal Profile:
Professional Interests:: robotics, computer vision, neural networks

Watch this Author's files

Files
Watch Lists

Files Posted by Mihail					1 - 1 of 1
Updated		File	Tags	Downloads (last 30 days)	Comments	Rating
11 Apr 2011		CNN - Convolutional neural network class This project provides matlab class for implementation of convolutional neural networks. Author: Mihail Sirotenko	neural network, image processing, classification, feature extraction, machine learning, ocr	115	15	4.88889 4.9 \| 9 ratings

Comments and Ratings by Mihail		View all 1 - 5 of 8
Updated	File	Comments	Rating
06 Feb 2012	CNN - Convolutional neural network class This project provides matlab class for implementation of convolutional neural networks. Author: Mihail Sirotenko	Full training cycle needs about 10 epochs on full training set with progressively decreasing theta. As far as I understand you did 1 epoch.
12 Jan 2012	CNN - Convolutional neural network class This project provides matlab class for implementation of convolutional neural networks. Author: Mihail Sirotenko	Regarding several last questions. I'm going to put new release of the lib which will contain example with faces and would be more convenient to use with various data. It already works in general. But I need a week or two more to finalize it since I do it in my free time.
03 Aug 2011	CNN - Convolutional neural network class This project provides matlab class for implementation of convolutional neural networks. Author: Mihail Sirotenko	2Gaurav. It means that file train_cnn.m have comments for almost every line of code, so you can find parameter you want to change and actually change it before start training. Basically train_cnn.m contains settings for network architecture (number of layers, number of neurons etc)
15 Oct 2010	CNN - Convolutional neural network class This project provides matlab class for implementation of convolutional neural networks. Author: Mihail Sirotenko	Thanks! Actually I had a plans to adapt this to face recognition, but unfortunately there're still only plans, because now I have absolutely no time to develop it. So I'd advice to look closely on preprocessing algorithms and try to make architecture similar to face detection papers advices.
30 Apr 2010	Sparseconv A fast convolution for one or more sparse vectors Author: G. Cuypers	Awesome! Just what I needed!

Comments and Ratings on Mihail's Files			View all 1 - 5 of 19
Updated	File	Comment by	Comments	Rating
06 Feb 2012	CNN - Convolutional neural network class This project provides matlab class for implementation of convolutional neural networks. Author: Mihail Sirotenko	Sirotenko, Mihail	Full training cycle needs about 10 epochs on full training set with progressively decreasing theta. As far as I understand you did 1 epoch.
28 Jan 2012	CNN - Convolutional neural network class This project provides matlab class for implementation of convolutional neural networks. Author: Mihail Sirotenko	Hu, Bo	This is a great job. However I have a question. I test this program using the MNIST handwritten digit database. The mcr rate is very high (about 15%) even I train the cnn using 10000 input. If I tried to train the cnn using 60000 input, then the program would took fairly long time, about several hours to finish. Anyway, the mcr is always about 15%. I wonder what parameter we should change to make the prediction accuracy higher. Thanks a lot.
12 Jan 2012	CNN - Convolutional neural network class This project provides matlab class for implementation of convolutional neural networks. Author: Mihail Sirotenko	Sirotenko, Mihail	Regarding several last questions. I'm going to put new release of the lib which will contain example with faces and would be more convenient to use with various data. It already works in general. But I need a week or two more to finalize it since I do it in my free time.
11 Jan 2012	CNN - Convolutional neural network class This project provides matlab class for implementation of convolutional neural networks. Author: Mihail Sirotenko	josé, chipo	hi please can any one help as to adapt this code to face recognition thanks
14 Nov 2011	CNN - Convolutional neural network class This project provides matlab class for implementation of convolutional neural networks. Author: Mihail Sirotenko	Ren, Zhipan

Top Tags Applied by Mihail	1 - 5 of 6
classification, feature extraction, image processing, machine learning, neural network

Files Tagged by Mihail					1 - 1 of 1
Updated		File	Tags	Downloads (last 30 days)	Comments	Rating
11 Apr 2011		CNN - Convolutional neural network class This project provides matlab class for implementation of convolutional neural networks. Author: Mihail Sirotenko	neural network, image processing, classification, feature extraction, machine learning, ocr	115	15	4.88889 4.9 \| 9 ratings

Currently Watching
Type	Description
Author	Alexander Huth
File	Fast 2D GPU-based convolution
File	CNN - Convolutional neural network class

Files Matching Mihail's Watch List					View all 1 - 3 of 3
Updated		File	Tags	Downloads (last 30 days)	Comments	Rating
11 Apr 2011		CNN - Convolutional neural network class This project provides matlab class for implementation of convolutional neural networks. Author: Mihail Sirotenko	neural network, image processing, classification, feature extraction, machine learning, ocr	115	15	4.88889 4.9 \| 9 ratings
16 Jul 2008		2D CUDA-based bilinear interpolation GPU assisted fast bilinear interpolation Author: Alexander Huth	fast mex, 2d bilinear interpola..., cuda	17	8	3.0 3.0 \| 1 rating
16 Jul 2008		Fast 2D GPU-based convolution Graphics chip assisted fast 2d convolution Author: Alexander Huth	cuda, 2d convolution, fast mex	24	12	4.2 4.2 \| 5 ratings

Comments and Ratings Matching Mihail's Watch List			1-5 of 31
Date	File	Comment by	Comments	Rating
06 Feb 2012	CNN - Convolutional neural network class This project provides matlab class for implementation of convolutional neural networks.	Mihail Sirotenko	Full training cycle needs about 10 epochs on full training set with progressively decreasing theta. As far as I understand you did 1 epoch.	Comment only
28 Jan 2012	CNN - Convolutional neural network class This project provides matlab class for implementation of convolutional neural networks.	Bo Hu	This is a great job. However I have a question. I test this program using the MNIST handwritten digit database. The mcr rate is very high (about 15%) even I train the cnn using 10000 input. If I tried to train the cnn using 60000 input, then the program would took fairly long time, about several hours to finish. Anyway, the mcr is always about 15%. I wonder what parameter we should change to make the prediction accuracy higher. Thanks a lot.	5
12 Jan 2012	CNN - Convolutional neural network class This project provides matlab class for implementation of convolutional neural networks.	Mihail Sirotenko	Regarding several last questions. I'm going to put new release of the lib which will contain example with faces and would be more convenient to use with various data. It already works in general. But I need a week or two more to finalize it since I do it in my free time.	Comment only
11 Jan 2012	CNN - Convolutional neural network class This project provides matlab class for implementation of convolutional neural networks.	chipo josé	hi please can any one help as to adapt this code to face recognition thanks	Comment only
14 Nov 2011	CNN - Convolutional neural network class This project provides matlab class for implementation of convolutional neural networks.	Zhipan Ren		5

Contact us at files@mathworks.com