Debiasing AI Using Amazon SageMaker

Focused View

Kesha Williams

1:42:27

231 View

1. Introduction

001. Debiasing AI using Amazon SageMaker.mp4

01:21

002. What you should know.mp4

00:26

2. Crime-Fighting Case Study

003. Predictive policing.mp4

02:42

004. Overview of crime-fighting case study.mp4

05:30

005. Architecture diagram.mp4

03:03

006. Tools, services, and costs.mp4

03:30

007. Terms and concepts.mp4

03:24

008. Demo of Amazon SageMaker.mp4

04:42

3. Building the Model via SageMaker

009. What is SageMaker.mp4

04:31

010. Machine learning process.mp4

04:08

011. Inspect and visualize data.mp4

09:03

012. Prepare the data.mp4

09:22

013. Train the model.mp4

05:54

014. Deploy the model.mp4

02:50

4. Deploying and Testing the Model via DeepLens

015. What is DeepLens.mp4

02:35

016. Deploy model to AWS DeepLens.mp4

06:35

017. Extend AWS DeepLens.mp4

06:56

018. Retrieve attributes via AWS Rekognition.mp4

05:36

019. Invoke the crime model.mp4

04:27

020. Set up model alerts.mp4

04:50

5. Explaining the Model

021. What is explainable AI (XAI).mp4

02:23

022. Trust and transparency issues.mp4

04:26

023. Making algorithms explainable.mp4

02:55

6. Conclusion

024. Next steps.mp4

01:18

Description

Artificial intelligence (AI) can have deeply embedded bias. It’s the job of data scientists and developers to ensure their algorithms are fair, transparent, and explainable. This responsibility is critically important when building models that may determine policy—or shape the course of people’s lives. In this course, award-winning software engineer Kesha Williams explains how to debias AI with Amazon SageMaker. She shows how to use SageMaker to create a predictive-policing machine-learning model that integrates Rekognition and AWS DeepLens, creating a crime-fighting model that can “see” what’s happening in a live scene. By following the development process, you can learn what goes into making a model that doesn’t suffer from cultural prejudices. Kesha also discusses how to remove bias in training data, test a model for fairness, and build trust in AI by making models that are explainable.

More details

User Reviews

Rating

average 0

Total votes0

Focused display

Artificial Intelligence

Selling on Amazon

Amazon PPC Advertising

Amazon Affiliate Marketing

Kesha Williams

Instructor's Courses

Kesha Williams is an award-winning technology leader with 26 years of experience in tech. She's passionate about hands-on building and developing the next generation of leaders. Forbes, Amazon Web Services (AWS), and Oracle have applauded her contributions to the technology community. She's recognized, by Amazon, as an AWS Machine Learning Hero, AWS Ambassador, and Alexa Champion. Her expertise in machine learning led her to the TED stage as a winner of TED's Spotlight Presentation Academy, where she trained with the TED Institute. She holds multiple AWS certifications and has leadership training from Harvard Business School. She serves on the Board of Directors for Women in Voice in her spare time. Learn more at http://www.kesha.tech

Linkedin Learning

View courses Linkedin Learning

LinkedIn Learning is an American online learning provider. It provides video courses taught by industry experts in software, creative, and business skills. It is a subsidiary of LinkedIn. All the courses on LinkedIn fall into four categories: Business, Creative, Technology and Certifications. It was founded in 1995 by Lynda Weinman as Lynda.com before being acquired by LinkedIn in 2015. Microsoft acquired LinkedIn in December 2016.