Pengoptimal

Pendahuluan TensorFlow di Python

Isaiah Hull

Visiting Associate Professor of Finance, BI Norwegian Business School

Cara menemukan minimum

Gambar menunjukkan Grand Canyon.

¹ Sumber: U.S. National Park Service

Cara menemukan minimum

Gambar menunjukkan Grand Canyon.

¹ Sumber: U.S. National Park Service

Cara menemukan minimum

Gambar menunjukkan Grand Canyon.

¹ Sumber: U.S. National Park Service

Gambar menunjukkan lintasan pembelajaran pengoptimal SGD, RMSprop, dan Adam untuk masalah sederhana.

Pengoptimal gradient descent

Pengoptimal stochastic gradient descent (SGD)
- tf.keras.optimizers.SGD()
- learning_rate
Sederhana dan mudah dipahami

Pengoptimal RMSprop

Pengoptimal root mean squared (RMS) propagation
- Menerapkan laju pembelajaran berbeda per fitur
- tf.keras.optimizers.RMSprop()
- learning_rate
- momentum
- decay
Memungkinkan momentum bertambah lalu berkurang

Pengoptimal Adam

Pengoptimal adaptive moment (Adam)
- tf.keras.optimizers.Adam()
- learning_rate
- beta1
Kinerja baik dengan nilai default

Contoh lengkap

import tensorflow as tf

# Define the model function
def model(bias, weights, features = borrower_features):
    product = tf.matmul(features, weights)
    return tf.keras.activations.sigmoid(product+bias)

# Compute the predicted values and loss
def loss_function(bias, weights, targets = default, features = borrower_features):
    predictions = model(bias, weights)
    return tf.keras.losses.binary_crossentropy(targets, predictions)

# Minimize the loss function with RMS propagation
opt = tf.keras.optimizers.RMSprop(learning_rate=0.01, momentum=0.9)
opt.minimize(lambda: loss_function(bias, weights), var_list=[bias, weights])

Ayo berlatih!

Pendahuluan TensorFlow di Python