Convolutional Neural Network (CNN)

73 Posts

Model that defeats KataGo, an open source Go-playing system
Convolutional Neural Network (CNN)

Champion Model Is No Go: Adversarial AI Beats Master KataGo Algorithm

A new algorithm defeated a championship-winning Go model using moves that even a middling human player could counter. Researchers trained a model to defeat KataGo, an open source Go-playing system that has beaten top human players.
Illustration of the Dialogue Transformer Language Model (DLM)
Convolutional Neural Network (CNN)

The Sound of Conversation: AI Learns to Mimic Conversational Pauses and Interruptions

In spoken conversation, people naturally take turns amid interjections and other patterns that aren’t strictly verbal. A new approach generated natural-sounding audio dialogs without training on text transcriptions that mark when one party should stop speaking and the other should chime in.
The Dark Side of the Moon — Lit Up! AI Illuminates Dark Regions of the Moon
Convolutional Neural Network (CNN)

The Dark Side of the Moon — Lit Up! AI Illuminates Dark Regions of the Moon

Neural networks are making it possible to view parts of the Moon that are perpetually shrouded by darkness. Researchers devised a method called Hyper-effective Noise Removal U-net Software (HORUS) to remove noise from images of the Moon’s south pole.
Animation showing 3 main types of data augmentation and random cropping of a picture
Convolutional Neural Network (CNN)

Cookbook for Vision Transformers: A Formula for Training Vision Transformers

Vision Transformers (ViTs) are overtaking convolutional neural networks (CNN) in many vision tasks, but procedures for training them are still tailored for CNNs. New research investigated how various training ingredients affect ViT performance.
Animated overview of PP-Matting
Convolutional Neural Network (CNN)

Automating Mattes for Visual Effects: New ML Method Produces Image Mattes Easier

Researchers at Baidu introduced PP-Matting, an architecture that, given an image, estimates the transparency of pixels surrounding foreground objects to create mattes without requiring additional input.
Animated flowcharts show how the ProtCNN AI model classifies proteins.
Convolutional Neural Network (CNN)

Protein Families Deciphered: Machine Learning Categorizes Proteins Based on Their Functions

Convolutional neural networks separate proteins into functional families without considering their shapes.
Illustration of a robot with a captain costume
Convolutional Neural Network (CNN)

Neural Networks: Find the Function — A Basic Introduction to Neural Networks

Let’s get this out of the way: A brain is not a cluster of graphics processing units, and if it were, it would run software far more complex than the typical artificial neural network. Yet neural networks were inspired by the brain’s architecture.
Shifted Patch Tokenization (SPT) | Locality Self-Attention (LSA)
Convolutional Neural Network (CNN)

Less Data for Vision Transformers: Boosting Vision Transformer Performance with Less Data

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.
Graphs showing how app Face2Gene works
Convolutional Neural Network (CNN)

The Many Faces of Genetic Illness: Face recognition identifies childhood genetic diseases.

People with certain genetic disorders share common facial features. Doctors are using computer vision to identify such syndromes in children so they can get early treatment.
Group of pigs
Convolutional Neural Network (CNN)

Barnyard Sentiment Analysis: AI calculates a pig's mood using snorts.

Neural networks may help farmers make sure their animals are happy. Researchers led by Elodie Briefer and Ciara Sypherd at University of Copenhagen developed a system that interprets the moods behind a pig’s grunts and squeals.
Overview of Mobile-Former | Cross attention over the entire featuremap for the first token in Mobile→Former
Convolutional Neural Network (CNN)

High Accuracy at Low Power: An energy efficient method for computer vision.

Equipment that relies on computer vision while unplugged — mobile phones, drones, satellites, autonomous cars — need power-efficient models. A new architecture set a record for accuracy per computation.
Transformer Architecture
Convolutional Neural Network (CNN)

Transformers See in 3D: Using transformers to visualize depth in 2D images.

Visual robots typically perceive the three-dimensional world through sequences of two-dimensional images, but they don’t always know what they’re looking at. For instance, Tesla’s self-driving system has been known to mistake a full moon for a traffic light.
A living room made out of cups of coffee: the people, the seats, the chimney, the lamp, all gather around a cozy fire.
Convolutional Neural Network (CNN)

One Architecture to Do Them All: Transformer: The AI architecture that can do it all.

The transformer architecture extended its reach to a variety of new domains.What happened: Originally developed for natural language processing, transformers are becoming the Swiss Army Knife of deep learning.
Equivariant subsampling on 1D feature maps with a scale factor c = 2.
Convolutional Neural Network (CNN)

Image Transformations Unmasked: CNNs for vision that aren't fooled by changing backgrounds.

If you change an image by moving its subject within the frame, a well trained convolutional neural network may not recognize the fundamental similarity between the two versions. New research aims to make CNN wise to such alterations.
Animated image showing different Zillow listings
Convolutional Neural Network (CNN)

Price Prediction Turns Perilous: How Covid Broke Zillow's Pricing Algorithm

The real-estate website Zillow bought and sold homes based on prices estimated by an algorithm — until Covid-19 confounded the model’s predictive power. Zillow, whose core business is providing real-estate information for prospective buyers, shut down its house-flipping division after...

Subscribe to The Batch

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