Forward propagation

Introduction to Deep Learning in Python

Dan Becker

Data Scientist and contributor to Keras and TensorFlow libraries

Bank transactions example

  • Make predictions based on:
    • Number of children
    • Number of existing accounts
Introduction to Deep Learning in Python

Forward propagation

ch1_2.007.png

Introduction to Deep Learning in Python

Forward propagation

ch1_2.008.png

Introduction to Deep Learning in Python

Forward propagation

ch1_2.009.png

Introduction to Deep Learning in Python

Forward propagation

ch1_2.010.png

Introduction to Deep Learning in Python

Forward propagation

ch1_2.011.png

Introduction to Deep Learning in Python

Forward propagation

ch1_2.012.png

Introduction to Deep Learning in Python

Forward propagation

ch1_2.013.png

Introduction to Deep Learning in Python

Forward propagation

ch1_2.014.png

Introduction to Deep Learning in Python

Forward propagation

ch1_2.015.png

Introduction to Deep Learning in Python

Forward propagation

ch1_2.016.png

Introduction to Deep Learning in Python

Forward propagation

ch1_2.017.png

Introduction to Deep Learning in Python

Forward propagation

ch1_2.018.png

Introduction to Deep Learning in Python

Forward propagation

ch1_2.019.png

Introduction to Deep Learning in Python

Forward propagation

ch1_2.020.png

Introduction to Deep Learning in Python

Forward propagation

ch1_2.021.png

Introduction to Deep Learning in Python

Forward propagation

ch1_2.022.png

Introduction to Deep Learning in Python

Forward propagation

ch1_2.023.png

Introduction to Deep Learning in Python

Forward propagation

ch1_2.024.png

Introduction to Deep Learning in Python

Forward propagation

  • Multiply - add process
  • Dot product
  • Forward propagation for one data point at a time
  • Output is the prediction for that data point
Introduction to Deep Learning in Python

Forward propagation code

import numpy as np
input_data = np.array([2, 3])
weights = {'node_0': np.array([1, 1]),
           'node_1': np.array([-1, 1]),
           'output': np.array([2, -1])}
node_0_value = (input_data * weights['node_0']).sum()
node_1_value = (input_data * weights['node_1']).sum()
Introduction to Deep Learning in Python

Forward propagation code

hidden_layer_values = np.array([node_0_value, node_1_value])

print(hidden_layer_values)

[5, 1]

output = (hidden_layer_values * weights['output']).sum()

print(output)

9
Introduction to Deep Learning in Python

Let's practice!

Introduction to Deep Learning in Python

Preparing Video For Download...