|
1 | 1 | # Bees-CNN-Algorithm |
2 | | -A Fuzzy Evolutionary Deep Leaning |
| 2 | +%% Bees CNN Algorithm (A Fuzzy Evolutionary Deep Leaning) - Created in 20 Jan 2022 by Seyed Muhammad Hossein Mousavi |
| 3 | +% It is possible to fit deep learning weights and bias using evolutionary |
| 4 | +% algorithm, right after training stage. Here, CNN is used to classify 8 |
| 5 | +% face classes. After CNN train, initial fuzzy model is created to aid the |
| 6 | +% learning process. Finally, CNN network weights (from Fully Connected Layer) |
| 7 | +% trains using Bees algorithm |
| 8 | +% to be fitted in a nature inspired manner (here behavior of Bees). You can |
| 9 | +% used your data with any number of samples and classes. Remember, code's |
| 10 | +% parameters are adjusted for this data and if you want to replace your |
| 11 | +% data you may have to change the parameters. Image data is in 64*64 size and |
| 12 | +% in 2 dimensions and stored in 'CNNDat' folder. So, important parameters |
| 13 | +% are as below: |
| 14 | +% 1. |
| 15 | +% 'numTrainFiles' = you have to change this based on number of your samples |
| 16 | +% in each class. for example if each class has 120 sample, 90 is good |
| 17 | +% enough as 90 samples considered for train and others for test. |
| 18 | +% 2. |
| 19 | +% 'imageInputLayer' = it is size of your image data like [64 64 1] |
| 20 | +% 3. |
| 21 | +% 'fullyConnectedLayer' = it is number of your classes like (8) |
| 22 | +% 4. |
| 23 | +% 'MaxEpochs' = the more the better and more computation run time like 40 |
| 24 | +% 5. |
| 25 | +% 'ClusNum' = Fuzzy C Means (FCM) Cluster Number like 3 or 4 is nice |
| 26 | +% 6. |
| 27 | +% These two are from "BEEFCN.m" function : |
| 28 | +% 'Params.MaxIt' = it is iteration number in Bees algorithm. 20 is good |
| 29 | +% 'Params.nScoutBee' = it is population number in Bees algorithm. Like 10. |
| 30 | +% ------------------------------------------------ |
| 31 | +% Feel free to contact me if you find any problem using the code: |
| 32 | +% Author: SeyedMuhammadHosseinMousavi |
| 33 | +% My Email: mosavi.a.i.buali@gmail.com |
| 34 | +% My Google Scholar: https://scholar.google.com/citations?user=PtvQvAQAAAAJ&hl=en |
| 35 | +% My GitHub: https://github.com/SeyedMuhammadHosseinMousavi?tab=repositories |
| 36 | +% My ORCID: https://orcid.org/0000-0001-6906-2152 |
| 37 | +% My Scopus: https://www.scopus.com/authid/detail.uri?authorId=57193122985 |
| 38 | +% My MathWorks: https://www.mathworks.com/matlabcentral/profile/authors/9763916# |
| 39 | +% my RG: https://www.researchgate.net/profile/Seyed-Mousavi-17 |
| 40 | +% ------------------------------------------------ |
| 41 | +% Hope it help you, enjoy the code and wish me luck :) |
| 42 | + |
| 43 | + |
0 commit comments