Machine Learning Research

195 Posts

Image Generation + Probabilities
Machine Learning Research

Image Generation + Probabilities

If you want to both synthesize data and find the probability of any given example — say, generate images of manufacturing defects to train a defect detector and identify the highest-probability defects — you may use the architecture known as a

3 min read
Efficiency Experts
Machine Learning Research

Efficiency Experts

The emerging generation of trillion-parameter language models take significant computation to train. Activating only a portion of the network at a time can cut the requirement dramatically and still achieve exceptional results.

3 min read
More Realistic Pictures From Text
Machine Learning Research

More Realistic Pictures From Text

OpenAI’s DALL·E got an upgrade that takes in text descriptions and produces images in styles from hand-drawn to photorealistic. The new version is a rewrite from the ground up. It uses the earlier CLIP zero-shot image classifier to represent

2 min read
Learning After Overfitting
Machine Learning Research

Learning After Overfitting

When a model trains too much, it can overfit, or memorize, the training data, which reduces its ability to analyze similar-but-different inputs. But what if training continues? New work found that overfitting isn’t the end of the line.

2 min read
Barnyard Sentiment Analysis
Machine Learning Research

Barnyard Sentiment Analysis

Neural networks may help farmers make sure their animals are happy. Researchers led by Elodie Briefer and Ciara Sypherd at the University of Copenhagen developed a system that interprets the moods behind a pig’s grunts and squeals.

2 min read
Who Needs Training?
Machine Learning Research

Who Needs Training?

When you’re training a neural network, it takes a lot of computation to optimize its weights using an iterative algorithm like stochastic gradient descent. Wouldn’t it be great to compute the best parameter values in one pass? A new method takes a

3 min read
Investorbots: Too Good to Be True?
Machine Learning Research

Investorbots: Too Good to Be True?

Machine learning models aren’t likely to replace human stock-market analysts any time soon, a new study concluded.

2 min read
High-Energy Deep Learning
Machine Learning Research

High-Energy Deep Learning

Nuclear fusion technology, long touted as an unlimited source of safe, clean energy, took a step toward reality with a machine learning algorithm that molds the fuel in a reactor’s core.

3 min read
Multimodal AI Takes Off
Machine Learning Research

Multimodal AI Takes Off

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

2 min read
Trillions of Parameters
Machine Learning Research

Trillions of Parameters

The trend toward ever-larger models crossed the threshold from immense to ginormous. Google kicked off 2021 with Switch Transformer, the first published work to exceed a trillion parameters, weighing in at 1.6 trillion.

2 min read
Richer Video Representations
Machine Learning Research

Richer Video Representations

To understand a movie scene, viewers often must remember or infer previous events and extrapolate potential consequences. New work improved a model’s ability to do the same.What's new: Rowan Zellers a

2 min read
Different Strokes for Robot Folks
Machine Learning Research

Different Strokes for Robot Folks

A neural network can make a photo resemble a painting via neural style transfer, but it can also learn to reproduce an image by applying brush strokes. A new method taught a system this painterly skill without any training data.

2 min read
Crawl the Web, Absorb the Bias
Machine Learning Research

Crawl the Web, Absorb the Bias

The emerging generation of trillion-parameter models needs datasets of billions of examples, but the most readily available source of examples on that scale — the web — is polluted with bias and antisocial expressions. A new study examines the issue.

2 min read
Transformer Speed-Up Sped Up
Machine Learning Research

Transformer Speed-Up Sped Up

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

2 min read
Search Goes Multimodal
Machine Learning Research

Search Goes Multimodal

Google will upgrade its search engine with a new model that tracks the relationships between words, images, and, in time, videos — the first fruit of its latest research into multimodal machine learning and multilingual language modeling.

2 min read

Subscribe to The Batch

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