myCNN

myCNN is a Matlab implementation of convolutional neural network (CNN).

Version 1.4.0 (1.06 MB)
11.4K Downloads
(10)
30 Sep 2009
Download

  • Install in MATLAB

    Requires R2026b and later. Learn more
Download

  • Install in MATLAB

    Requires R2026b and later. Learn more

You are now following this Submission

Cite As

Nikolay Chumerin (2026). myCNN (https://au.mathworks.com/matlabcentral/fileexchange/25247-mycnn), MATLAB Central File Exchange. Retrieved .

Acknowledgements

Inspired by: CNN - Convolutional neural network class

Categories

Find more on Deep Learning Toolbox in Help Center and MATLAB Answers

General Information

MATLAB Release Compatibility

  • Compatible with any release

Platform Compatibility

  • Windows
  • macOS
  • Linux
Open in new tab
Version Published Release Notes
1.4.0

- a graphical demo (demo_myCNN) added (thanks to Mikhail Sitotenko, submission 24291)
- an example of pretrained network (myLeNet5-example.mat) added
- the myCNN constructor is fixed (loading from file)
Download

  • Install in MATLAB

    Requires R2026b and later. Learn more
1.3.0

- the first attempt to make the M-layer trainable
- a new private functions unfold.m and unfold2.m added
- soft_max now suppots n-dimensional array (not only 2D and 3D)
- improved myCNN object description
Download

  • Install in MATLAB

    Requires R2026b and later. Learn more
1.2.0

see ChangeLog inside the archive.
Download

  • Install in MATLAB

    Requires R2026b and later. Learn more
1.1.0

- fixed some bugs related to system dependencies;
- added ChangeLog and content.m;
- more comments in the example.
Download

  • Install in MATLAB

    Requires R2026b and later. Learn more
1.0.0

Download

  • Install in MATLAB

    Requires R2026b and later. Learn more