Gradient descent

경사하강법

import numpy as np
import tensorflow as tf
from tensorflow.keras.models import Sequential

데이터 소개

x_train = [1,2,3,4]
y_train=[0,-1,-2,-3]

tf.model=tf.keras.Sequential()

모델링

• units==output shape
• input_dim == input shape

tf.model.add(tf.keras.layers.Dense(units=1,input_dim=1))

• SGD == standard gradient descendent, lr==learning rate(=step size)

sgd=tf.keras.optimizers.SGD(lr=0.1)

• MSE == mean_sqaure_error, 1/m * sig(y'-y)^2

tf.model.complie(loss='mse', optimizer=sgd)

print summary of the model to the terminal

tf.model.summary()

fit() executes training

• fit은 트레이닝 해라 (반복문 포함)

tf.model.fit(x_train, y_train, epochs=200)

predict() returns predicted value

y_predict=tf.model.predict(np.array([5,4]))
print(y_predict)

출력 결과

[[-3.9975324]
 [-2.9987302]]