Animation showing optimizing a physical design
Machine Learning Research

Airfoils Automatically Optimized

Engineers who design aircraft, aqueducts, and other objects that interact with air and water use numerical simulations to test potential shapes, but they rely on trial and error to improve their designs. A neural simulator can optimize the shape itself.
2 min read
Variational Neural Cellular Automata (VNCA) overview
Machine Learning Research

Tech Imitates Life, Life Imitates Art

The computational systems known as cellular automata reproduce patterns of pixels by iteratively applying simple rules based loosely on the behavior of biological cells. New work extends their utility from reproducing images to generating new ones.
3 min read
The framework of Virtual Outlier Synthesis (VOS)
Machine Learning Research

Right-Sizing Confidence

An object detector trained exclusively on urban images might mistake a moose for a pedestrian and express high confidence in its poor judgment. New work enables object detectors, and potentially other neural networks, to lower their confidence when they encounter unfamiliar inputs.
2 min read
Driver one passing driver two who has no gas
Machine Learning Research

Linear Regression: Straight & Narrow

Linear regression may be the key statistical method in machine learning, but it didn’t get to be that way without a fight. Two eminent mathematicians claimed credit for it, and 200 years later the matter remains unresolved.
2 min read
Architecture of CXV
Machine Learning Research

Upgrade for Vision Transformers

Vision Transformer and models like it use a lot of computation and memory when processing images. New work modifies these architectures to run more efficiently while adopting helpful properties from convolutions.
2 min read
Didactic diagram of a hypothetical embedded-model architecture
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 normalizing flow.
3 min read
Shifted Patch Tokenization (SPT) | Locality Self-Attention (LSA)
Machine Learning Research

Less Data for Vision Transformers

Vision Transformer (ViT) outperformed convolutional neural networks in image classification, but it required more training data. New work enabled ViT and its variants to outperform other architectures with less training data.
2 min read
GLaM model architecture
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
AI generated images with different descriptions
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 text descriptions.
2 min read
Jurassic-X's software infrastructure
Machine Learning Research

Neural Nets + Rules = Truer Text

A new approach aims to cure text generators of their tendency to produce nonsense. AI21 Labs launched Jurassic-X, a natural language processing system that combines neural networks and rule-based programs.
2 min read
Deep Symbolic Regression
Machine Learning Research

From Sequences to Symbols

Given a sequence of numbers, neural networks have proven adept at discovering a mathematical expression that generates it. New work uses transformers to extend that success to a further class of expressions.
2 min read
Grokking: A dramatic example of generalization far after overfitting on an algorithmic dataset
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
Stock Market Simulation using cGANs
Machine Learning Research

Stock-Trading Test Bed

If you buy or sell stocks, it’s handy to test your strategy before you put real money at risk. Researchers devised a fresh approach to simulating market behavior.
3 min read
Overview of Graph Hyper Network (GHN-2)
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 substantial step in that direction.
3 min read
Coordinating Robot Limbs
Machine Learning Research

Coordinating Robot Limbs

A dog doesn’t think twice about fetching a tennis ball, but an autonomous robot typically suffers from delays between perception and action. A new machine-learning model helped a quadruped robot coordinate its sensors and actuators.
2 min read

Subscribe to The Batch

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