Views
No views yet
pip install neat-optimizer1git clone https://github.com/yourusername/neat-optimizer.git
2cd neat-optimizer
3pip install -e .1import tensorflow as tf
2from neat_optimizer import NEATOptimizer
3
4# Create your model
5model = tf.keras.Sequential([
6 tf.keras.layers.Dense(128, activation='relu'),
7 tf.keras.layers.Dense(10, activation='softmax')
8])
9
10# Use NEAT optimizer
11optimizer = NEATOptimizer(
12 learning_rate=0.001,
13 noise_scale=0.01,
14 beta_1=0.9,
15 beta_2=0.999
16)
17
18# Compile and train
19model.compile(
20 optimizer=optimizer,
21 loss='sparse_categorical_crossentropy',
22 metrics=['accuracy']
23)
24
25model.fit(x_train, y_train, epochs=10, validation_data=(x_val, y_val))learning_rate (float, default=0.001): Initial learning ratenoise_scale (float, default=0.01): Scale of noise injectionbeta_1 (float, default=0.9): Exponential decay rate for first moment estimatesbeta_2 (float, default=0.999): Exponential decay rate for second moment estimatesepsilon (float, default=1e-7): Small constant for numerical stabilitynoise_decay (float, default=0.99): Decay rate for noise scale over time1@software{neat_optimizer,
2 title={NEAT: Noise-Enhanced Adaptive Training Optimizer},
3 author={Your Name},
4 year={2025},
5 url={https://github.com/yourusername/neat-optimizer}
6}