Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/jmcheon/data_science
https://github.com/jmcheon/data_science
multilayer-perceptron neuralnetwork-creation python3 pytorch tensorflow
Last synced: about 2 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/jmcheon/data_science
- Owner: jmcheon
- Created: 2024-05-15T12:55:42.000Z (8 months ago)
- Default Branch: main
- Last Pushed: 2024-06-26T15:32:31.000Z (6 months ago)
- Last Synced: 2024-06-26T18:47:59.917Z (6 months ago)
- Topics: multilayer-perceptron, neuralnetwork-creation, python3, pytorch, tensorflow
- Language: Jupyter Notebook
- Homepage:
- Size: 18.2 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Data Science
## Circular Data
### Hyperparameters
```
lr = 1e-3
batch_size = None
epochs = 30
optimizer = optimizers.SGD(learning_rate=lr)
loss = BCELoss()
metrics = ['accuracy']
validation_data = (x_val, y_val)
```
### 1-layer Multilayer Perceptron
```
Model(
Dense((2, 1), activation=Sigmoid)
)
```
#### Training
Learning Curves
#### Evaluation
Metric
Train
Validation
Test
Accuracy
0.5527
0.54
0.5625
### 2-layer Multilayer Perceptron
```
Model(
Dense((2, 2), activation=ReLU)
Dense((2, 1), activation=Sigmoid)
)
```
#### Training
Learning Curves
#### Evaluation
Metric
Train
Validation
Test
Accuracy
0.7847
0.825
0.7375
### 3-layer Multilayer Perceptron
```
Model(
Dense((2, 4), activation=ReLU)
Dense((4, 3), activation=ReLU)
Dense((3, 1), activation=Sigmoid)
)
```
#### Training
Learning Curves
#### Evaluation
Metric
Train
Validation
Test
Accuracy
0.8916
0.89
0.8
### 4-layer Multilayer Perceptron
```
Model(
Dense((2, 10), activation=ReLU)
Dense((10, 8), activation=ReLU)
Dense((8, 5), activation=ReLU)
Dense((5, 1), activation=Sigmoid)
)
```
#### Training
Learning Curves
#### Evaluation
Metric
Train
Validation
Test
Accuracy
0.9986
1.0
1.0