Stanford University

43 Posts

Animated chart shows how AI can avoid mistaking an image's subject for its context.
Stanford University

Taming Spurious Correlations: New Technique Helps AI Avoid Classification Mistakes

When a neural network learns image labels, it may confuse a background item for the labeled object. New research avoids such mistakes.
2 min read
Animated charts show how scientists misuse machine learning.
Stanford University

Bad Machine Learning Makes Bad Science: Is Machine Learning Driving a Scientific Reproducibility Crisis?

A recent workshop highlighted the impact of poorly designed AI models in medicine, security, software engineering, and other disciplines.
1 min read
Man sitting on a tree with a monkey and a gorilla
Stanford University

Decision Trees: From Root to Leaves

What kind of beast was Aristotle? The philosopher's follower Porphyry, who lived in Syria during the third century, came up with a logical way to answer the question. He organized Aristotle’s proposed “categories of being” from general to
3 min read
AI: A Progress Report
Stanford University

AI: A Progress Report

A new study showcases AI’s growing importance worldwide.What’s new: The fifth annual AI Index from Stanford University’s Institute for Human-Centered AI documents rises in funding, regulation, and performance.
2 min read
Multimodal AI Takes Off: Multimodal Models, such as CLIP and Dall-E, Are Taking Over AI
Stanford University

Multimodal AI Takes Off: Multimodal Models, such as CLIP and Dall-E, Are Taking Over AI

While models like GPT-3 and EfficientNet, which work on text and images respectively, are responsible for some of deep learning’s highest-profile successes, approaches that find relationships between text and images made impressive
1 min read
Halloween family portrait showing the inheritance of some spooky characteristics
Stanford University

New Models Inherit Old Flaws: AI Models May Inherit Flaws From Previous Systems

Is AI becoming inbred? The fear: The best models increasingly are fine-tuned versions of a small number of so-called foundation models that were pretrained on immense quantities of data scraped from the web.
1 min read
A new framework that helps models “unlearn” information selectively and incrementally
Stanford University

Deep Unlearning: AI Researchers Teach Models to Unlearn Data

Privacy advocates want deep learning systems to forget what they’ve learned. What’s new: Researchers are seeking ways to remove the influence of particular training examples, such as an individual’s personal information, from a trained model without affecting its performance, Wired reported.
1 min read
Series of images showing some of the findings of the new study by researchers at Stanford’s Human AI Institute
Stanford University

Weak Foundations Make Weak Models: Foundation AI Models Pass Flaws to Fine-Tuned Variants

A new study examines a major strain of recent research: huge models pretrained on immense quantities of uncurated, unlabeled data and then fine-tuned on a smaller, curated corpus.
2 min read
Graphs, images and data related to the activation function known as ReLU
Stanford University

Upgrade for ReLU

The activation function known as ReLU builds complex nonlinear functions across layers of a neural network, making functions that outline flat faces and sharp edges. But how much of the world breaks down into perfect polyhedra?
2 min read
Examples of image generators using GANsformer
Stanford University

Attention for Image Generation

Attention quantifies how each part of one input affects the various parts of another. Researchers added a step that reverses this comparison to produce more convincing images.
2 min read
Graphs and data related to ImageNet performance
Stanford University

ImageNet Performance: No Panacea

It’s commonly assumed that models pretrained to achieve high performance on ImageNet will perform better on other visual tasks after fine-tuning. But is it always true? A new study reached surprising conclusions.
2 min read
Selected data from AI Index, an annual report from Stanford University
Stanford University

AI for Business Is Booming

Commercial AI research and deployments are on the rise, a new study highlights. The latest edition of the AI Index, an annual report from Stanford University, documents key trends in the field including the growing importance of private industry and the erosion of U.S. dominance in research.
2 min read
Different data related to the phenomenon called underspecification
Stanford University

Facing Failure to Generalize

The same models trained on the same data may show the same performance in the lab, and yet respond very differently to data they haven’t seen before. New work finds this inconsistency to be pervasive.
2 min read
Art pieces with subjective commentary regarding their emotional impact
Stanford University

How Art Makes AI Feel

An automated art critic spells out the emotional impact of images. Led by Panos Achlioptas, researchers at Ecole Polytechnique, King Abdullah University, and Stanford University trained a deep learning system to generate subjective interpretations of art.
2 min read
Stanford University

Pain Points in Black and White

A model designed to assess medical patients’ pain levels matched the patients’ own reports better than doctors’ estimates did — when the patients were Black.
1 min read

Subscribe to The Batch

Stay updated with weekly AI News and Insights delivered to your inbox