Series of images with graphs and data related to optimization algorithms
Machine Learning Research

When Optimization is Suboptimal

Bias arises in machine learning when we fit an overly simple function to a more complex problem. A theoretical study shows that gradient descent itself may introduce such bias and render algorithms unable to fit data properly.
2 min read
Graphs and data related to language models and image processing
Machine Learning Research

Transforming Pixels

Language models like Bert, Ernie, and Elmo have achieved spectacular results based on clever pre-training approaches. New research applies some of those Sesame Street lessons into image processing.
2 min read
Data related to Covid-19 symptoms prediction
Machine Learning Research

Cats Cured of Covid

Neural networks are famously bad at interpreting input that falls outside the training set’s distribution, so it’s not surprising that some models are certain that cat pictures show symptoms of Covid-19. A new approach won’t mistakenly condemn your feline to a quarantine.
2 min read
Graphs and data related to Ordered Temporal Alignment Module (Otam)
Machine Learning Research

Less (Video) is More (Examples)

We’d all love to be able to find similar examples of our favorite cat videos. But few of us want to label thousands of similar videos of even the cutest kitties. New research makes headway in video classification when training examples are scarce.
2 min read
Data related to a new reinforcement learning approach
Machine Learning Research

Eyes on the Prize

When the chips are down, humans can track critical details without being distracted by irrelevancies. New research helps reinforcement learning models similarly focus on the most important details.
2 min read
Information and data related to Category-based Subspace Attention Network (CSA-Net)
Machine Learning Research

Which Shoes Go With That Outfit?

Need a wardrobe upgrade? You could ask the fashion mavens at Netflix’s Queer Eye — or you could use a new neural network. Researchers at Amazon propose Category-based Subspace Attention Network (CSA-Net) to predict and retrieve compatible garments and accessories that complement one another.
2 min read
Examples of clothes image-text combo search
Machine Learning Research

That Online Boutique, But Smarter

Why search for “a cotton dress shirt with button-down collar, breast pockets, barrel cuffs, scooped hem, and tortoise shell buttons in grey” when a photo and the words “that shirt, but grey” will do the trick? A new network understands the image-text combo.
2 min read
Examples of detection of animals in images using Detection Transformer (DETR).
Machine Learning Research

Computer Vision Transformed

The transformer architecture that has shaken up natural language processing may replace recurrent layers in object detection networks. A Facebook team led by Nicolas Carion and Francisco Massa simplified object detection pipelines by using transformers, yielding Detection Transformer (DETR).
1 min read
Images and graphs related to Dense Steerable Filter CNN (DSF-CNN)
Machine Learning Research

Seeing Straight at Any Rotation

A cat rotated by any number of degrees is still a cat. It takes a lot of rotated training images to teach convolutional filters this simple fact. A new filter design has this common-sense knowledge built-in.
2 min read
Operation of a virtual fitting room
Machine Learning Research

Clothes Make the Model

In online retailing, the most common customer complaints are slow shipping and inability to try on clothes. Amazon conceived its Prime program to address the first concern. To answer the second, it built a virtual fitting room.
2 min read
Information related to the Once-for-All (OFA) method
Machine Learning Research

Build Once, Run Anywhere

From server to smartphone, devices with less processing speed and memory require smaller networks. Instead of building and training separate models to run on a variety of hardware, a new approach trains a single network that can be adapted to any device.
2 min read
Excerpt from study about models that learn to predict task-specific distance metrics
Machine Learning Research

Misleading Metrics

A growing body of literature shows that some steps in AI’s forward march may actually move sideways. A new study questions advances in metric learning.
2 min read
Illustration of Amazon Alexa with a question mark inside of a thought bubble
Machine Learning Research

What Were We Talking About?

Conversational agents have a tough job following the zigs and zags of human conversation. They’re getting better at it — thanks to yesterday’s technology. Amazon recently improved the Alexa chatbot’s ability to identify the current topic of conversation.
1 min read
Illustration of two translators on a scale
Machine Learning Research

Choosing Words Carefully

The words “big” and “large” have similar meanings, but they aren’t always interchangeable: You wouldn’t refer to an older, male sibling as your “large brother” (unless you meant to be cheeky). Choosing among words with similar meanings is critical in language tasks like translation.
2 min read
Illustration of a doctor and a nurse
Machine Learning Research

Gender Bender

AI learns human biases: In word vector space, “man is to computer programmer as woman is to homemaker,” as one paper put it. New research helps language models unlearn such prejudices.
2 min read

Subscribe to The Batch

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