Fungsi loss

Pendahuluan TensorFlow di Python

Isaiah Hull

Visiting Associate Professor of Finance, BI Norwegian Business School

Pengantar fungsi loss

Operasi tensorflow yang mendasar
- Digunakan untuk melatih model
- Ukuran kecocokan model
Nilai lebih tinggi -> kecocokan lebih buruk
- Minimalkan fungsi loss

Fungsi loss umum di TensorFlow

TensorFlow memiliki operasi untuk fungsi loss umum
- Mean squared error (MSE)
- Mean absolute error (MAE)
- Huber error
Fungsi loss tersedia di tf.keras.losses()
- tf.keras.losses.mse()
- tf.keras.losses.mae()
- tf.keras.losses.Huber()

Mengapa kita peduli pada fungsi loss?

Gambar ini menampilkan fungsi loss MSE, MAE, dan Huber pada interval -2 hingga 2.

MSE
- Sangat menghukum outlier
- Sensitivitas (gradien) tinggi dekat minimum
MAE
- Skala linear dengan besar error
- Sensitivitas rendah dekat minimum
Huber
- Mirip MSE dekat minimum
- Mirip MAE jauh dari minimum

Mendefinisikan fungsi loss

# Import TensorFlow under standard alias
import tensorflow as tf

# Compute the MSE loss
loss = tf.keras.losses.mse(targets, predictions)

Mendefinisikan fungsi loss

# Define a linear regression model
def linear_regression(intercept, slope = slope, features = features):
    return intercept + features*slope

# Define a loss function to compute the MSE
def loss_function(intercept, slope, targets = targets, features = features):
    # Compute the predictions for a linear model
    predictions = linear_regression(intercept, slope)

    # Return the loss
    return tf.keras.losses.mse(targets, predictions)

Mendefinisikan fungsi loss

# Compute the loss for test data inputs
loss_function(intercept, slope, test_targets, test_features)

10.77

# Compute the loss for default data inputs
loss_function(intercept, slope)

5.43

Ayo berlatih!

Pendahuluan TensorFlow di Python