Business
AI Goes Underground: Computer Vision From SewerAI Classifies Defective Pipes
A system from California startup SewerAI analyzes videos of underground pipes to prioritize those in need of repair.
Classification
Machine Learning Research
Transformer Speed-Up Sped Up: How to Speed Up Image Transformers
The transformer architecture is notoriously inefficient when processing long sequences — a problem in processing images, which are essentially long sequences of pixels. One way around this is to break up input images and process the pieces
Machine Learning Research
Oddball Recognition: New Method Identifies Outliers in AI Training Data
Models trained using supervised learning struggle to classify inputs that differ substantially from most of their training data. A new method helps them recognize such outliers.
Tech & Society
Risk Reduction for Elders: AI System Helps Elderly Stay on Their Feet
Deep learning is helping to protect elderly people from potentially catastrophic tumbles.What’s happening: More than 2,000 senior living facilities across the U.S. use a diagnostic system called VirtuSense Balance
Machine Learning Research
Revenge of the Perceptrons: Perceptrons do some AI tasks on par with complex AI.
Why use a complex model when a simple one will do? New work shows that the simplest multilayer neural network, with a small twist, can perform some tasks as well as today’s most sophisticated architectures.
Tech & Society
Shots in the Dark: Evidence shows Shotspotter altered evidence for police.
A crime-fighting AI company altered evidence to please police, a new investigation claims — the latest in a rising chorus of criticism. ShotSpotter modified the system’s findings in some cases.
Science
Bugbot: How AI can help with the insect biodiversity crisis.
An insect-sorting robot could help scientists grapple with the global biodiversity crisis. An automated insect classifier sucks in tiny arthropods, classifies them, and maps their most important identifying features.
Machine Learning Research
Pattern for Efficient Learning: A training method for few-shot learning in computer vision.
Getting high accuracy out of a classifier trained on a small number of examples is tricky. You might train the model on several large-scale datasets prior to few-shot training, but what if the few-shot dataset includes novel classes? A new method performs well even in that case.
Science
Sorting Shattered Traditions: Archaeologists use machine learning to classify pottery.
Computer vision is probing the history of ancient pottery | What’s new: Researchers at Northern Arizona University developed a machine learning model that identifies different styles of Native American painting on ceramic fragments and sorts the shards by historical period.
Machine Learning Research
The Writing, Not the Doodles: A handwriting detection AI model for messy paper.
Systems designed to turn handwriting into text typically work best on pages with a consistent layout, such as a single column unbroken by drawings, diagrams, or extraneous symbols. A new system removes that requirement.
Business
Tesla All-In For Computer Vision: Tesla cut radar from its self-driving system.
Tesla is abandoning radar in favor of a self-driving system that relies entirely on cameras. The electric car maker announced it will no longer include radar sensors on Model 3 sedans and Model Y compact SUVs sold in North America.
Tech & Society
Radiologists Eye AI: Radiologists increasingly rely upon computer vision.
AI lately has achieved dazzling success interpreting X-rays and other medical imagery in the lab. Now it’s catching on in the clinic. Roughly one-third of U.S. radiologists use AI in some form in their work.