Lesson List

Welcome to the Nanodegree program

The Skills That Set You Apart

The Data Science Process

Learn the data science process, including how to build effective data visualizations, and how to communicate with various stakeholders

Communicating to Stakeholders

Project Write A Data Science Blog Post

In this project, learners will choose a dataset, identify three questions, and analyze the data to find answers to these questions. They will create a GitHub repository with their project, and write a blog post to communicate their findings to the appropriate audience. This project will help learners reinforce and extend their knowledge of machine learning, data visualization, and communication.

Introduction to Software Engineering

In this lesson, you’ll write production-level code and practice object-oriented programming, which you can integrate into machine learning projects.

Software Engineering Practices Pt I

Software Engineering Practices Pt II

OOP

Portfolio Exercise: Upload a Package to PyPi

Web Development

Portfolio Exercise: Deploy a Data Dashboard

Introduction to Data Engineering

ETL Pipelines

Introduction to NLP

Learn Natural Language Processing one of the fields with the most real applications of Deep Learning

Machine Learning Pipelines

Disaster Response Pipeline

Project1: Disaster Response Pipeline

Concepts in Experiment Design

Statistical Considerations in Testing

Statistical Considerations in Testing

AB Testing Case Study

A/B Testing Case Study

Portfolio Exercise Starbucks

Introduction to Recommendation Engines

Matrix Factorization for Recommendations

Recommendation Engines

Upcoming Lesson

Sentiment Prediction RNN

Convolutional Neural Networks

Transfer Learning

Weight Initialization

Autoencoders

Job Search

Find your dream job with continuous learning and constant effort

Refine Your Entry-Level Resume

Craft Your Cover Letter

Optimize Your GitHub Profile

Develop Your Personal Brand

Go to course home
01. Introduction

In this lesson, we are going to take a look at how we can improve our models using one of SageMaker’s features. In particular, we are going to explore how we can use SageMaker to perform hyperparameter tuning.

In many machine learning models there are some parameters that need to be specified by the model creator and which can’t be determined directly from the data itself. Generally the approach to finding the best parameters is to train a bunch of models with different parameters and then choose the model that works best.

SageMaker provides an automated way of doing this. In fact, SageMaker also does this in an intelligent way using Bayesian optimization. What we will do is specify ranges for our hyperparameters. Then, SageMaker will explore different choices within those ranges, increasing the performance of our model over time.

In addition to learning how to use hyperparameter tuning, we will look at Amazon’s CloudWatch service. For our purposes, CloudWatch provides a user interface through which we can examine various logs generated during training. This can be especially useful when diagnosing errors.

Previous
Next