You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+14-25Lines changed: 14 additions & 25 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -24,8 +24,8 @@
24
24
25
25
26
26
MetaPerceptron (Metaheuristic-optimized Multi-Layer Perceptron) is a Python library that implements variants and the
27
-
traditional version of Multi-Layer Perceptron models. These include Metaheuristic-optimized MLP models (GA, PSO, WOA, TLO, DE, ...)
28
-
and Gradient Descent-optimized MLP models (SGD, Adam, Adelta, Adagrad, ...). It provides a comprehensive list of
27
+
traditional version of Multi-Layer Perceptron models. These include Metaheuristic-trained MLP models (GA, PSO, WOA, TLO, DE, ...)
28
+
and Gradient Descent-trained MLP models (SGD, Adam, Adelta, Adagrad, ...). It provides a comprehensive list of
29
29
optimizers for training MLP models and is also compatible with the Scikit-Learn library. With MetaPerceptron,
30
30
you can perform searches and hyperparameter tuning using the features provided by the Scikit-Learn library.
31
31
@@ -44,22 +44,21 @@ you can perform searches and hyperparameter tuning using the features provided b
44
44
45
45
# Citation Request
46
46
47
-
If you want to understand how Metaheuristic is applied to Multi-Layer Perceptron, you need to read the paper
48
-
titled **"Let a biogeography-based optimizer train your Multi-Layer Perceptron"**.
49
-
The paper can be accessed at the following [link](https://doi.org/10.1016/j.ins.2014.01.038)
47
+
If you want to understand how Metaheuristic is applied to Multi-Layer Perceptron, you need to read the paper [link](https://doi.org/10.1016/j.csi.2025.103977)
50
48
51
49
52
50
Please include these citations if you plan to use this library:
53
51
54
52
```code
55
-
@software{nguyen_van_thieu_2023_10251022,
56
-
author = {Nguyen Van Thieu},
57
-
title = {MetaPerceptron: A Standardized Framework for Metaheuristic-Trained Multi-Layer Perceptron},
Copy file name to clipboardExpand all lines: docs/source/pages/support.rst
+12-5Lines changed: 12 additions & 5 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -2,15 +2,22 @@
2
2
Citation Request
3
3
================
4
4
5
-
Note::
6
-
7
-
If you want to understand how Metaheuristic is applied to Multi-Layer Perceptron, you need to read the paper
8
-
titled `Let a biogeography-based optimizer train your Multi-Layer Perceptron`.
9
-
The paper can be accessed at the following `this link <https://doi.org/10.1016/j.ins.2014.01.038>`_
5
+
If you want to understand how Metaheuristic is applied to Multi-Layer Perceptron, you need to read the paper `link <https://doi.org/10.1016/j.csi.2025.103977>`_
10
6
11
7
12
8
Please include these citations if you plan to use this library::
13
9
10
+
@article{van2025metaperceptron,
11
+
title={MetaPerceptron: A Standardized Framework for Metaheuristic-Driven Multi-Layer Perceptron Optimization},
12
+
author={Van Thieu, Nguyen and Mirjalili, Seyedali and Garg, Harish and Hoang, Nguyen Thanh},
13
+
journal={Computer Standards \& Interfaces},
14
+
pages={103977},
15
+
year={2025},
16
+
publisher={Elsevier},
17
+
doi={10.1016/j.csi.2025.103977},
18
+
url={https://doi.org/10.1016/j.csi.2025.103977}
19
+
}
20
+
14
21
@software{nguyen_van_thieu_2023_10251022,
15
22
author = {Nguyen Van Thieu},
16
23
title = {MetaPerceptron: A Standardized Framework for Metaheuristic-Trained Multi-Layer Perceptron},
0 commit comments