Deep Learning with Python

Understand the basics of deep learning and explore how Python's TensorFlow and Keras libraries can be used for creating deep learning models.

Introduction

Deep Learning is a subfield of machine learning that uses algorithms inspired by the structure and function of the brain’s neural networks. Python provides libraries like TensorFlow and Keras which makes it a great language for deep learning. This lesson will introduce the basics of deep learning and how to use TensorFlow and Keras for creating deep learning models.

Learning Objectives

• Understand what deep learning is and its relation to artificial neural networks.
• Learn how to use the TensorFlow and Keras libraries for deep learning.

What is Deep Learning?

Deep learning is a machine learning technique that teaches computers to do what comes naturally to humans: learn by example. It is a key technology behind driverless cars, enabling them to recognize a stop sign, or to distinguish a pedestrian from a lamppost.

Introduction to TensorFlow

TensorFlow is a free and open-source software library for machine learning and artificial intelligence. It can be used across a range of tasks but has a particular focus on training and inference of deep neural networks.

import tensorflow as tf

# Create a constant tensor
hello = tf.constant('Hello, TensorFlow!')

# To access a Tensor value, call numpy().
print(hello.numpy())

Introduction to Keras

Keras is a user-friendly neural network library written in Python, and it’s included with TensorFlow. Keras makes it really easy for ML beginners to build and design a neural network. Install TensorFlow with pip install tensorflow.

from tensorflow import keras

# Define the model
model = keras.Sequential([
    keras.Input(shape=(100,)),                     # 100 numbers in
    keras.layers.Dense(64, activation='relu'),     # a hidden layer of 64 neurons
    keras.layers.Dense(10, activation='softmax'),  # 10 outputs, one per class
])

# Compile the model
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])

model.summary()

This builds a small network but doesn’t train it yet. Training is done with model.fit() once you have some data.

Summary

In this lesson, you’ve learned about the basics of deep learning and its relation to artificial neural networks. We introduced TensorFlow, a library for large-scale machine learning, and Keras, a high-level neural networks API that runs on top of TensorFlow. These powerful tools open up a wide range of possibilities for training deep learning models.

< Previous Next >

You can use the arrows  ← → on your keyboard to navigate between lessons.