Neural Networks and Deep Learning (0)

About this Course

In the first course of the Deep Learning Specialization, you will study the foundational concept of neural networks and deep learning.

By the end, you will be familiar with the significant technological trends driving the rise of deep learning; build, train, and apply fully connected deep neural networks; implement efficient (vectorized) neural networks; identify key parameters in a neural network’s architecture; and apply deep learning to your applications.

The Deep Learning Specialization is our foundational program that will help you understand the capabilities, challenges, and consequences of deep learning and prepare you to participate in developing leading-edge AI technology. It provides a pathway for you to gain the knowledge and skills to apply machine learning to your work, level up your technical career, and take the definitive step in AI.

728x90

Introduction to Deep Learning

Analyze the major trends driving the rise of deep learning, and give examples of where and how it is applied today.

Learning Objectives

---

• Discuss the major trends driving the rise of deep learning.
• Explain how deep learning is applied to supervised learning
• List the major categories of models (CNNs, RNNs, etc.), and when they should be applied
• Assess appropriate use cases for deep learning

Introduction to Deep Learning

What is a Neural Network?

012

A neural network consists of the input, hidden, and output layers.

The input layer is where we input the data into the model, the hidden layer is where the neurons do all the hard work, and the output layer comes up with a guess to match our goals.

True or false? As explained in this lecture, every input layer feature is interconnected with every hidden layer feature.

True

Supervised Learning with Neural Networks

012

Supervised learning is a method to train neural networks with data and answers to get close to the given answer.

We can think of structured data as tables and unstructured data as everything else.

Would structured or unstructured data have features such as pixel values or individual words?

Unstructured data

Why is Deep Learning taking off?

 

01

With the increase in the amount of data and the advancement of computation and algorithms, we are seeing an improvement in deep learning. 

What will the variable m denote in this course?

Number of training examples

All the information provided is based on the Deep Learning Specialization | Coursera from DeepLearning.AI