learn-co-curriculum / dsc-enterprise-deloitte-dl-neural-networks-section-intro

Introduction

Introduction

In this section, you'll be introduced to one of the most advanced machine learning algorithms in the world currently, neural networks! Here are the topics we'll be covering in this section.

Objectives

You will be able to:

• Understand and explain what is covered in this section
• Understand and explain why the section will help you to become a data scientist

Introduction to Deep Learning

The time has come to learn about one of the most exciting and fast-moving areas of data science: Deep Learning! When we talk about deep learning, we talk about (deep) neural networks. You'll learn all about them in this section. You'll also use Python to build (basic) neural networks from scratch.

Introduction to Neural Networks

In this section, you'll learn what it means when we talk about neural networks. You'll learn about the essential building blocks like "layers", "nodes", "arrows", "weights", "loss", "cost function", etc. You'll learn that a neural network general consists of several layers, and how a logistic regression model can be represented as a neural network with just one layer. You'll be able to explain what the advantages and disadvantages of using neural networks are, and get an insight of how forward and backward propagation are used in neural networks to minimize the loss and "optimize" your neural network.

Introduction to Keras

You'll be introduced to Keras, open source neural network library in Python, which makes building neural networks surprisingly easy. Before building your first neural network model in Keras, you'll learn about tensors and why they are important when building deep learning models.

Summary

In this section, you'll learn the basics of neural networks and how to implement them in keras!