oikan 0.0.2.2__tar.gz → 0.0.2.3__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: oikan
3
- Version: 0.0.2.2
3
+ Version: 0.0.2.3
4
4
  Summary: OIKAN: Optimized Interpretable Kolmogorov-Arnold Networks
5
5
  Author: Arman Zhalgasbayev
6
6
  License: MIT
@@ -17,7 +17,7 @@ Dynamic: license-file
17
17
 
18
18
  <!-- logo in the center -->
19
19
  <div align="center">
20
- <img src="docs/media/oikan_logo.png" alt="OIKAN Logo" width="200"/>
20
+ <img src="https://raw.githubusercontent.com/silvermete0r/oikan/main/docs/media/oikan_logo.png" alt="OIKAN Logo" width="200"/>
21
21
 
22
22
  <h1>OIKAN: Optimized Interpretable Kolmogorov-Arnold Networks</h1>
23
23
  </div>
@@ -71,13 +71,11 @@ from sklearn.model_selection import train_test_split
71
71
  # Initialize model with optimal architecture
72
72
  model = OIKANRegressor(
73
73
  hidden_dims=[16, 8], # Network architecture
74
- num_basis=10, # Number of basis functions
75
- degree=3, # Polynomial degree
76
74
  dropout=0.1 # Regularization
77
75
  )
78
76
 
79
77
  # Fit model (sklearn-style)
80
- model.fit(X_train, y_train, epochs=200, lr=0.01)
78
+ model.fit(X_train, y_train, epochs=100, lr=0.01)
81
79
 
82
80
  # Get predictions
83
81
  y_pred = model.predict(X_test)
@@ -99,7 +97,7 @@ from oikan.model import OIKANClassifier
99
97
 
100
98
  # Similar sklearn-style interface for classification
101
99
  model = OIKANClassifier(hidden_dims=[16, 8])
102
- model.fit(X_train, y_train)
100
+ model.fit(X_train, y_train, epochs=100, lr=0.01)
103
101
  probas = model.predict_proba(X_test)
104
102
 
105
103
  # Save classification formulas with implementation guidelines
@@ -148,7 +146,7 @@ OIKAN implements a novel neuro-symbolic architecture based on Kolmogorov-Arnold
148
146
 
149
147
  ### Architecture Diagram
150
148
 
151
- ![Architecture Diagram](docs/media/oikan_model_architecture_v0.0.2.2.png)
149
+ ![Architecture Diagram](https://raw.githubusercontent.com/silvermete0r/oikan/main/docs/media/oikan_model_architecture_v0.0.2.2.png)
152
150
 
153
151
  ### Key Design Principles
154
152
 
@@ -1,6 +1,6 @@
1
1
  <!-- logo in the center -->
2
2
  <div align="center">
3
- <img src="docs/media/oikan_logo.png" alt="OIKAN Logo" width="200"/>
3
+ <img src="https://raw.githubusercontent.com/silvermete0r/oikan/main/docs/media/oikan_logo.png" alt="OIKAN Logo" width="200"/>
4
4
 
5
5
  <h1>OIKAN: Optimized Interpretable Kolmogorov-Arnold Networks</h1>
6
6
  </div>
@@ -54,13 +54,11 @@ from sklearn.model_selection import train_test_split
54
54
  # Initialize model with optimal architecture
55
55
  model = OIKANRegressor(
56
56
  hidden_dims=[16, 8], # Network architecture
57
- num_basis=10, # Number of basis functions
58
- degree=3, # Polynomial degree
59
57
  dropout=0.1 # Regularization
60
58
  )
61
59
 
62
60
  # Fit model (sklearn-style)
63
- model.fit(X_train, y_train, epochs=200, lr=0.01)
61
+ model.fit(X_train, y_train, epochs=100, lr=0.01)
64
62
 
65
63
  # Get predictions
66
64
  y_pred = model.predict(X_test)
@@ -82,7 +80,7 @@ from oikan.model import OIKANClassifier
82
80
 
83
81
  # Similar sklearn-style interface for classification
84
82
  model = OIKANClassifier(hidden_dims=[16, 8])
85
- model.fit(X_train, y_train)
83
+ model.fit(X_train, y_train, epochs=100, lr=0.01)
86
84
  probas = model.predict_proba(X_test)
87
85
 
88
86
  # Save classification formulas with implementation guidelines
@@ -131,7 +129,7 @@ OIKAN implements a novel neuro-symbolic architecture based on Kolmogorov-Arnold
131
129
 
132
130
  ### Architecture Diagram
133
131
 
134
- ![Architecture Diagram](docs/media/oikan_model_architecture_v0.0.2.2.png)
132
+ ![Architecture Diagram](https://raw.githubusercontent.com/silvermete0r/oikan/main/docs/media/oikan_model_architecture_v0.0.2.2.png)
135
133
 
136
134
  ### Key Design Principles
137
135
 
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: oikan
3
- Version: 0.0.2.2
3
+ Version: 0.0.2.3
4
4
  Summary: OIKAN: Optimized Interpretable Kolmogorov-Arnold Networks
5
5
  Author: Arman Zhalgasbayev
6
6
  License: MIT
@@ -17,7 +17,7 @@ Dynamic: license-file
17
17
 
18
18
  <!-- logo in the center -->
19
19
  <div align="center">
20
- <img src="docs/media/oikan_logo.png" alt="OIKAN Logo" width="200"/>
20
+ <img src="https://raw.githubusercontent.com/silvermete0r/oikan/main/docs/media/oikan_logo.png" alt="OIKAN Logo" width="200"/>
21
21
 
22
22
  <h1>OIKAN: Optimized Interpretable Kolmogorov-Arnold Networks</h1>
23
23
  </div>
@@ -71,13 +71,11 @@ from sklearn.model_selection import train_test_split
71
71
  # Initialize model with optimal architecture
72
72
  model = OIKANRegressor(
73
73
  hidden_dims=[16, 8], # Network architecture
74
- num_basis=10, # Number of basis functions
75
- degree=3, # Polynomial degree
76
74
  dropout=0.1 # Regularization
77
75
  )
78
76
 
79
77
  # Fit model (sklearn-style)
80
- model.fit(X_train, y_train, epochs=200, lr=0.01)
78
+ model.fit(X_train, y_train, epochs=100, lr=0.01)
81
79
 
82
80
  # Get predictions
83
81
  y_pred = model.predict(X_test)
@@ -99,7 +97,7 @@ from oikan.model import OIKANClassifier
99
97
 
100
98
  # Similar sklearn-style interface for classification
101
99
  model = OIKANClassifier(hidden_dims=[16, 8])
102
- model.fit(X_train, y_train)
100
+ model.fit(X_train, y_train, epochs=100, lr=0.01)
103
101
  probas = model.predict_proba(X_test)
104
102
 
105
103
  # Save classification formulas with implementation guidelines
@@ -148,7 +146,7 @@ OIKAN implements a novel neuro-symbolic architecture based on Kolmogorov-Arnold
148
146
 
149
147
  ### Architecture Diagram
150
148
 
151
- ![Architecture Diagram](docs/media/oikan_model_architecture_v0.0.2.2.png)
149
+ ![Architecture Diagram](https://raw.githubusercontent.com/silvermete0r/oikan/main/docs/media/oikan_model_architecture_v0.0.2.2.png)
152
150
 
153
151
  ### Key Design Principles
154
152
 
@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
4
4
 
5
5
  [project]
6
6
  name = "oikan"
7
- version = "0.0.2.2"
7
+ version = "0.0.2.3"
8
8
  description = "OIKAN: Optimized Interpretable Kolmogorov-Arnold Networks"
9
9
  authors = [{name = "Arman Zhalgasbayev"}]
10
10
  dependencies = [
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes