Graphs related to ImageNet error landscape

Rightsizing Neural Nets

How much data do we want? More! How large should the model be? Bigger! How much more and how much bigger? New research estimates the impact of dataset and model sizes on neural network performance.
Animated symbol of Covid-19 virus structure

AI Takes on Coronavirus

Machine learning thrives on data, but information about the novel coronavirus and the illness it produces has been either thin or hard to access. Now researchers are pooling resources to share everything we do know.
Graph related to imple Contrastive Learning (SimCLR)

Self-Supervised Simplicity

A simple linear classifier paired with a self-supervised feature extractor outperformed a supervised deep learning model on ImageNet, according to new research.
Info about radioactive data

X Marks the Dataset

Which dataset was used to train a given model? A new method makes it possible to see traces of the training corpus in a model’s output.
Clay tablet

The King’s Moleskine

Machine learning promises to streamline handling of tomorrow’s bureaucratic drudgery — and, it turns out, that of 2,500 years ago. Computer vision is helping researchers at the University of Chicago translate a massive collection of ancient records inscribed on clay tablets.
FixMatch example

Less Labels, More Learning

In small data settings where labels are scarce, semi-supervised learning can train models by using a small number of labeled examples and a larger set of unlabeled examples. A new method outperforms earlier techniques.
Some results from CB Insights' annual list of the 100 most promising startups in AI

Machine Learning Churning

Many of this year’s hottest AI companies are taking the spotlight from last year’s darlings.What’s new: CB Insights, which analyzes early-stage companies, published its annual list of the 100 “most promising” startups in AI.
Functioning of system that trackes the productivity of industrial workers

Eyes on the Assembly Line

AI may not steal your job, but it can tell the boss when you’re slacking. Drishti, a startup based in Palo Alto and Bengaluru, tracks the productivity of industrial workers by recognizing their actions on the assembly line.
Text "You only live once. #YOLO" written over an orange background

Code No Evil

A prominent AI researcher has turned his back on computer vision over ethical issues. The co-creator of the popular object-recognition network You Only Look Once (YOLO) said he no longer works on computer vision because the technology has “almost no upside and enormous downside risk.”
Fragment of a video explaining a model that extracts landmarks on the fly from radar scans

Locating Landmarks on the Fly

Directions such as “turn left at the big tree, go three blocks, and stop at the big red house on your left” can get you to your destination because they refer to stationary landmarks. New research enables self-driving cars to identify such stable indicators on their own.
Exercise training system working

Personal TrAIner

No more sloppy workouts: AI can correct your form. A home exercise system uses neural nets to analyze your motions and tell you when you perform a move properly, reports The Verge.
Information related to a test powered by deep learning that diagnoses tumor samples in only a few minutes

Surgical Speed-Up

Every second counts when a patient’s skull is open in the operating room. A new technique based on deep learning can shorten some brain surgeries. During brain cancer operations, surgeons must stop in mid-operation for up to a half hour while a pathologist analyzes the tumor tissue.
Information and images related to 6D-Pose Anchor-based Category-level Keypoint-tracker (6-PACK)

Deep Learning for Object Tracking

AI is good at tracking objects in two dimensions. A new model processes video from a camera with a depth sensor to predict how objects move through space.
The Tibot Spoutnic

Poultry in Motion

A top meat packer is counting its chickens with AI. Tyson Foods is using computer vision to track drumsticks, breasts, and thighs as they move through its processing plants, the Wall Street Journal reports.
Results of a technique that interprets reflected light to reveal objects outside the line of sight

Periscope Vision

Wouldn’t it be great to see around corners? Deep learning researchers are working on it. Researchers developed deep-inverse correlography, a technique that interprets reflected light to reveal objects outside the line of sight.

Subscribe to The Batch

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