Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

Introduction to Neural Networks with TensorFlow

Go to class Write review

Overview

Start your exploration of neural networks with a beginner's course on TensorFlow, using the scikit-learn Digits Dataset. Learn neural network basics and deep learning by developing, training, and evaluating models with TensorFlow. Understand different neural network architectures and improve them, emphasizing the importance of data preparation in deep learning.

Syllabus

Unit 1: Introduction to Neural Networks: TensorFlow and the Digits Dataset

Visualize an Image and Verify TensorFlow Version
Exploring Binary Color Map for Digit Images
Exploring Image Representation with Color Maps

Unit 2: Mastering Data Preprocessing for Neural Networks

Displaying the Flattened Digits Dataset
Shuffling Digits Dataset for Better Training
Standardizing Data for Neural Networks
Data Preprocessing: Fit or Fit-Transform?
Data Preprocessing for Neural Networks

Unit 3: Building Neural Networks with TensorFlow: A Beginner's Guide

Defining a Neural Network Model Architecture
Fix the Neural Network Model Architecture
Adding Hidden Layers to Neural Networks

Unit 4: Math Behind Neural Networks

Implementing the Sigmoid Activation Function
Implementing the ReLU Activation Function
Neuron Output Calculation Fix
Defining Second Layer of Neurons

Unit 5: Understanding and Applying Loss Functions and Optimizers in TensorFlow

Exploring the Neural Network Architecture
Applying Optimal Settings for Neural Network Compilation
Correcting Neural Network Errors
Building a Classification Neural Network

Unit 6: Training and Evaluating Neural Networks

Observe the Learning Trajectory of a Neural Network
Enhancing Neural Network Training with Epochs
Adding a Second Layer to the Neural Network
Modifying and Observing a Neural Network

Reviews

Start your review of Introduction to Neural Networks with TensorFlow