© Umberto Michelucci 2018
Umberto MichelucciApplied Deep Learninghttps://doi.org/10.1007/978-1-4842-3790-8_10

10. Logistic Regression from Scratch

Umberto Michelucci1 
(1)
toelt.ai, Dübendorf, Switzerland
 
In Chapter 2, we developed a logistic regression model for binary classification with one neuron and applied it to two digits of the MNIST dataset. The actual Python code for the computational graph construction was just ten lines of code (excluding the part that performs the training of the model; review Chapter 2, if you don’t remember what we did there).
tf.reset_default_graph()
X = tf.placeholder(tf.float32, [n_dim, None])
Y = tf.placeholder(tf.float32, [1, None])
learning_rate = tf.placeholder(tf.float32, shape=())
W = tf.Variable(tf.zeros([1, n_dim])) ...

Get Applied Deep Learning: A Case-Based Approach to Understanding Deep Neural Networks now with O’Reilly online learning.

O’Reilly members experience live online training, plus books, videos, and digital content from 200+ publishers.