The 2022 theme for International Women’s Day is #BreakTheBias. With that in mind, I decided to do a little experiment to see what GPT-3 can show us about the gender bias that’s built into our language.
Let’s start with a quick overview of GPT-3, in case you don’t spend as much time as I do having conversations with a machine: Basically, it’s an AI trained on pretty much every word written online to generate conversational language that sounds remarkably human.
Before I get into the part where I depress you, I want to be clear: GPT-3 is a tremendous achievement. An enormously big deal that will have far-ranging implications. That’s why it’s important that we don’t build it on a rotten foundation.
And the rotten foundation? That’s us. Read More
Daily Archives: March 10, 2022
One Thing to Fool them All: Generating Interpretable, Universal, andPhysically-Realizable Adversarial Features
It is well understood that modern deep networks are vulnerable to adversarial attacks. However, conventional attack methods fail to produce adversarial perturbations that are intelligible to humans, and they pose limited threats in the physical world. To study feature-class associations in networks and better understand their vulnerability to attacks in the real world, we develop feature-level adversarial perturbations using deep image generators and a novel optimization objective. We term these feature-fool attacks. We show that they are versatile and use them to generate targeted feature-level attacks at the ImageNet scale that are simultaneously interpretable, universal to any source image, and physically-realizable. These attacks reveal spurious, semantically-describable feature/class associations that can be exploited by novel combinations of objects. We use them to guide the design of “copy/paste” adversaries in which one natural image is pasted into another to cause a targeted misclassification. Read More
#adversarialSelf-taught Learning: Transfer Learning from Unlabeled Data
We present a new machine learning framework called “self-taught learning” for using unlabeled data in supervised classification tasks. We do not assume that the unlabeled data follows the same class labels or generative distribution as the labeled data. Thus, we would like to use a large number of unlabeled images (or audio samples, or text documents) randomly downloaded from the Internet to improve performance on a given image (or audio, or text) classification task. Such unlabeled data is significantly easier to obtain than in typical semi-supervised or transfer learning settings, making self-taught learning widely applicable to many practical learning problems. We describe an approach to self-taught learning that uses sparse coding to construct higher-level features using the unlabeled data. These features form a succinct input representation and significantly improve classification performance. When using an SVM for classification, we further show how a Fisher kernel can be learned for this representation. Read More
#self-supervisedWhy The Andy Warhol Diaries Recreated the Artist’s Voice With AI
The filmmakers had under four minutes of audio to work with. And yes, they considered the ethical concerns.
BACK IN 1982, Andy Warhol was, somewhat infamously, turned into a robot. The machine was made by a Disney Imagineering veteran for a project that never really took off, but Warhol liked his animatronic self. “Machines have less problems,” he once said. “I’d like to be a machine, wouldn’t you?” The artist, who died in 1987, was a master of his own cult of personality, and the robot was practically a manifestation of how the world perceived him: meticulously crafted, if a bit rigid and monotone in his conversational style.
… Even still, using an AI voice to speak for a beloved cultural figure—or anyone, really—isn’t without ethical quandaries. Rossi was already editing The Andy Warhol Diaries last summer when controversy erupted around director Morgan Neville using AI to recreate the voice of Anthony Bourdain for his doc Roadrunner. Rossi had been in consultation with the Andy Warhol Foundation about the AI recreation, and the Bourdain doc inspired a disclaimer that now appears a few minutes into Diaries stating that the voice was created with the Foundation’s permission. “When Andrew shared the idea of using an AI voice, I thought, ‘Wow, this is as bold as it is smart,’” says Michael Dayton Hermann, the foundation’s head of licensing. Read More
Restoring and attributing ancient texts using deep neural networks
Ancient history relies on disciplines such as epigraphy—the study of inscribed texts known as inscriptions—for evidence of the thought, language, society and history of past civilizations1. However, over the centuries, many inscriptions have been damaged to the point of illegibility, transported far from their original location and their date of writing is steeped in uncertainty. Here we present Ithaca, a deep neural network for the textual restoration, geographical attribution and chronological attribution of ancient Greek inscriptions. Ithaca is designed to assist and expand the historian’s workflow. The architecture of Ithaca focuses on collaboration, decision support and interpretability. While Ithaca alone achieves 62% accuracy when restoring damaged texts, the use of Ithaca by historians improved their accuracy from 25% to 72%, confirming the synergistic effect of this research tool. Ithaca can attribute inscriptions to their original location with an accuracy of 71% and can date them to less than 30 years of their ground-truth ranges, redating key texts of Classical Athens and contributing to topical debates in ancient history. This research shows how models such as Ithaca can unlock the cooperative potential between artificial intelligence and historians, transformationally impacting the way that we study and write about one of the most important periods in human history. Read More
Rick's Cafe AI 