Big Data News Hubb
Advertisement
  • Home
  • Big Data
  • News
  • Contact us
No Result
View All Result
  • Home
  • Big Data
  • News
  • Contact us
No Result
View All Result
Big Data News Hubb
No Result
View All Result
Home Big Data

Reducing Bias and Improving Safety in DALL·E 2

admin by admin
January 25, 2023
in Big Data


Today, we are implementing a new technique so that DALL·E generates images of people that more accurately reflect the diversity of the world’s population. This technique is applied at the system level when DALL·E is given a prompt describing a person that does not specify race or gender, like “firefighter.”

Based on our internal evaluation, users were 12× more likely to say that DALL·E images included people of diverse backgrounds after the technique was applied. We plan to improve this technique over time as we gather more data and feedback.


A photo of a CEO

Generate

In April, we started previewing the DALL·E 2 research to a limited number of people, which has allowed us to better understand the system’s capabilities and limitations and improve our safety systems.

During this preview phase, early users have flagged sensitive and biased images which have helped inform and evaluate this new mitigation.

We are continuing to research how AI systems, like DALL·E, might reflect biases in its training data and different ways we can address them.

During the research preview we have taken other steps to improve our safety systems, including:

  • Minimizing the risk of DALL·E being misused to create deceptive content by rejecting image uploads containing realistic faces and attempts to create the likeness of public figures, including celebrities and prominent political figures.
  • Making our content filters more accurate so that they are more effective at blocking prompts and image uploads that violate our content policy while still allowing creative expression.
  • Refining automated and human monitoring systems to guard against misuse.

These improvements have helped us gain confidence in the ability to invite more users to experience DALL·E.

Expanding access is an important part of our deploying AI systems responsibly because it allows us to learn more about real-world use and continue to iterate on our safety systems.



Source link

Previous Post

Building Custom Runtimes with Editors in Cloudera Machine Learning

Next Post

Crypto Custody: A Guide to Safekeeping Your Digital Assets

Next Post

Crypto Custody: A Guide to Safekeeping Your Digital Assets

Recommended

SANS Institute uses Amazon QuickSight to drive transformational security awareness maturity within organizations

April 13, 2023

How Databricks improved query performance by up to 2.2x by automatically optimizing file sizes

May 23, 2023

Accelerate Analytics for All – Cloudera Blog

January 26, 2023

Don't miss it

News

Trakstar unlocks new analytical opportunities for its HR customers with Amazon QuickSight

June 5, 2023
News

Saving Sea Turtles with SAS’s ConserVision App

June 5, 2023
News

8 Tips on Using Data for Ecommerce

June 4, 2023
Big Data

Video Highlights: Fine Tune GPT-J 6B in Under 3 Hours on IPUs

June 4, 2023
Big Data

Adaptive Query Execution in Structured Streaming

June 4, 2023
News

Migrate from Google BigQuery to Amazon Redshift using AWS Glue and Custom Auto Loader Framework

June 4, 2023
big-data-footer-white

© Big Data News Hubb All rights reserved.

Use of these names, logos, and brands does not imply endorsement unless specified. By using this site, you agree to the Privacy Policy and Terms & Conditions.

Navigate Site

  • Home
  • Big Data
  • News
  • Contact us

Newsletter Sign Up

No Result
View All Result
  • Home
  • Big Data
  • News
  • Contact us

© 2022 Big Data News Hubb All rights reserved.