1. Home
2. Training Library
3. Big Data
4. Courses
5. Getting Started With Deep Learning: Working With Data: Gradient Descent

# Exercise 1

Developed with

1
Introduction
PREVIEW1m 22s
3
4
12
13
EWMA
4m 12s
14
17
18
20
22
24
26

## The course is part of these learning paths

AWS Machine Learning – Specialty Certification Preparation
39
14
15
Start course
Overview
Difficulty
Beginner
Duration
1h 45m
Students
604
Ratings
5/5
Description

Learn about the importance of gradient descent and backpropagation, under the umbrella of Data and Machine Learning, from Cloud Academy.

From the internals of a neural net to solving problems with neural networks to understanding how they work internally, this course expertly covers the essentials needed to succeed in machine learning.

Learning Objective

• Understand the importance of gradient descent and backpropagation
• Be able to build your own neural network by the end of the course

Prerequisites

Transcript

Hey guys, welcome back. In this video, we'll review exercise one of section four. In exercise one of section four, we're asked to predict whether or not some people will be diagnosed diabetes from a set of variables of exams. So this is the population of Pima Indians. It's a very famous dataset that we got from UCI and it contains information about the patients including pregnancies, glucose, blood pressure, and then a few other medical examinations, and the last column is the outcome which is a binary variable. So it's a classification problem, and you're guided through a series of steps that go from loading the data, creating a histogram to inspect the features, and exploring the correlations between the features and the outcome column. We suggest using the seaborn pairplot, but you can also draw a heat map as we saw in the lecture.

Then there are a few open questions. Do features need standardization? And if so, what kind? Are we gonna use MinMax or standard? And then finally, prepare x and y using a machine learning model. Do you need dummy columns? And make sure you define your target variable. So as usual, try to do the exercise first, and then feel free to watch the video with the solution. Good luck.