Get the App
SLTechnology News&Howtos  ›  Development  › 

How to build a neural network through Tensorflow

Shulou Source: shulou.com Published: 2022-06-01 11:21:04 11月18日 Update

Today, the editor will share with you the relevant knowledge points about how to build a neural network through Tensorflow. The content is detailed and the logic is clear. I believe most people still know too much about this knowledge, so share this article for your reference. I hope you can get something after reading this article.

Tensorlow structure import tensorflow as tfimport numpy as np # create data x_data = np.random.rand (np.float32) y_data = x_data*0.1+0.3 # create a tensorlow structure weights = tf.Variable (tf.random_uniform ([1],-1.0,1.0)) # one dimension Biases = tf.Variable (tf.zeros ([1])) y = weights*x_data + biases loss = tf.reduce_mean (tf.square (y-y_data)) # mean square error function # establish optimizer to reduce error and improve parameter accuracy. Each iteration optimizes optimizer = tf.train.GradientDescentOptimizer (0.5) # learning rate of 0.5 (

Tags: Function activation input output signal data learning neural network only loss noise attribute knowledge article structure neural network minimum intact parameter Apple Docker Huawei Linux macOS MariaDB Microsoft MySQL NVidia OPPO Reno Linux Shulou Technology Microsoft Xiaomi NVidia