Image processing technique explained
Machine Learning Research

Preserving Detail in Image Inputs

Given real-world constraints on memory and processing time, images are often downsampled before they’re fed into a neural network. But the process removes fine details, and that degrades accuracy. A new technique squeezes images with less compromise.
2 min read
Graphs related to double descent
Machine Learning Research

Moderating the ML Roller Coaster

Wait a minute — we added training data, and our model’s performance got worse?! New research offers a way to avoid so-called double descent.
2 min read
Information and data related to the meta-algorithm AutoML-Zero
Machine Learning Research

Beyond Neural Architecture Search

Faced with a classification task, an important step is to browse the catalog of machine learning architectures to find a good performer. Researchers are exploring ways to do it automatically.
2 min read
Data and graphs related to batch normalization
Machine Learning Research

Outside the Norm

Batch normalization is a technique that normalizes layer outputs to accelerate neural network training. But new research shows that it has other effects that may be more important.
2 min read
Data and graphs related to equations that optimize some training parameters.
Machine Learning Research

Optimize Your Training Parameters

Last week we reported on a formula to determine model width and dataset size for optimal performance. A new paper contributes equations that optimize some training parameters.
2 min read
Robotic hand identifying transparent objects
Machine Learning Research

Seeing the See-Through

Glass bottles and crystal bowls bend light in strange ways. Image processing networks often struggle to separate the boundaries of transparent objects from the background that shows through them. A new method sees such items more accurately.
2 min read
Data related to model that predicts molecules that are structurally unrelated to known antibiotics
Machine Learning Research

Deep Learning Finds New Antibiotic

Chemists typically develop new antibiotics by testing close chemical relatives of tried-and-true compounds like penicillin. That approach becomes less effective, though, as dangerous bacteria evolve resistance to those very chemical structures. Instead, researchers enlisted neural networks.
2 min read
Graph related to error landscape
Machine Learning Research

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.
2 min read
Graph related to imple Contrastive Learning (SimCLR)
Machine Learning Research

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.
2 min read
Info about radioactive data
Machine Learning Research

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.
2 min read
FixMatch example
Machine Learning Research

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.
2 min read
Method overview of model that makes a person on video appear to speak words from a separate audio recording
Machine Learning Research

Guest Speaker

Deepfake videos in which one person appears to speak another’s words have appeared in entertainment, advertising, and politics. New research ups the ante for an application that enables new forms of both creative expression and
2 min read
Data related to Reformer
Machine Learning Research

Transformers Transformed

Transformer networks have revolutionized natural language processing, but they hog processor cycles and memory. New research demonstrates a more frugal variation.
2 min read
Fragment of a video explaining a model that extracts landmarks on the fly from radar scans
Machine Learning Research

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.
2 min read
Information related to a test powered by deep learning that diagnoses tumor samples in only a few minutes
Machine Learning Research

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.
2 min read

Subscribe to The Batch

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