Researchers at The University of Texas at Austin have developed what they believe is the first machine unlearning method applied to image-based generative AI. This method offers the ability to look under the hood and actively block and remove any violent images or copyrighted works without losing the rest of the information in the model.
Image-to-image models are the primary focus of this research. They take an input image and transform it — such as creating a sketch, changing a particular scene and more — based on a given context or instruction.
This new machine unlearning algorithm provides the ability of a machine learning model to “forget” or remove content if it is flagged for any reason without the need for retraining the model from scratch. Human teams handle the moderation and removal of content, providing an extra check on the model and ability to respond to user feedback.
Brian Wang is a Futurist Thought Leader and a popular Science blogger with 1 million readers per month. His blog Nextbigfuture.com is ranked #1 Science News Blog. It covers many disruptive technology and trends including Space, Robotics, Artificial Intelligence, Medicine, Anti-aging Biotechnology, and Nanotechnology.
Known for identifying cutting edge technologies, he is currently a Co-Founder of a startup and fundraiser for high potential early-stage companies. He is the Head of Research for Allocations for deep technology investments and an Angel Investor at Space Angels.
A frequent speaker at corporations, he has been a TEDx speaker, a Singularity University speaker and guest at numerous interviews for radio and podcasts. He is open to public speaking and advising engagements.
Soon to be used to purge the last remnants of non-woke thinking from the models.
And to remove woke & other unwanted dishonest things from the successful mass market models the people will gravitate to.
Seriously most people don’t care for bad data.
the most honest, or least obvious liar of an AI will get the lions share of the AI market, like google did during the early days of search, people will gravitate to the best over time.
teaching an AI to place politics or other dogma’s over honesty will hinder everything it does, you can see it with googles AI now, it can’t stop injecting wokeness into its answers, even those where it’s not applicable.
That’s because it’s got a moderately sensible training base, which by itself would not produce nearly woke enough results, so they take the prompt you provide and run it through a separate model that “wokeifies” it.
So you ask Gemini for “a picture of a leprechaun”. That goes to the wokeification engine, which passes on to Gemini a prompt requesting “Pictures of diverse leprechauns of a variety of races, ethnicities, and genders, which must include blacks and females”
Then Gemini satisfies the modified prompt, and you’re “This makes no sense!”
But, of course, Gemini is under orders not to tell you this.