Introduction to Neural Networks

6 hours of instruction

This course gives students the first preview of the world of Neural Networks and how they work. These state-of- the-art methods build powerful predictive systems and find latent patterns in large amounts of data. By the end of this course, students will learn the foundations of this complex topic and acquire practical skills to build neural networks in order to solve real-world problems.

OBJECTIVES

1. Define core applications and use cases for deep learning
2. Build foundational neural network models

PREREQUISITES

Optimizing Ensemble Methods

SYLLABUS & TOPICS COVERED

1. Basics
   • Introduction to neural networks
   • Neural networks use cases
2. Building Neural Networks
   • Create a basic neural network model
   • Evaluating models using various performance metrics
   • Visualize accuracy and loss
3. Intro To Tensor Flow
   • Overview of TensorFlow / Keras building blocks
   • Implement and fit a neural network model using Tensorflow on train data
   • Evaluating neural network model on test data

SOFTWARE REQUIREMENTS

You will have access to a Python-based JupyterHub environment for this course. No additional download or installation is required.