Key machine learning datasets are riddled with mistakes. Several benchmark datasets are shot through with incorrect labels. On average, 3.4 percent of examples in 10 commonly used datasets are mislabeled and the detrimental impact of such errors rises with model size.
Key machine learning datasets are riddled with mistakes. Several benchmark datasets are shot through with incorrect labels. On average, 3.4 percent of examples in 10 commonly used datasets are mislabeled and the detrimental impact of such errors rises with model size.
A recent generative adversarial network (GAN) produced more coherent images using modified transformers that replaced fully connected layers with convolutional layers. A new GAN achieved a similar end using transformers in their original form.
Some doctors don’t trust a second opinion when it comes from an AI system. A team at MIT and Regensburg University investigated how physicians responded to diagnostic advice they received from a machine learning model versus a human expert.
Some doctors don’t trust a second opinion when it comes from an AI system. A team at MIT and Regensburg University investigated how physicians responded to diagnostic advice they received from a machine learning model versus a human expert.
The same models trained on the same data may show the same performance in the lab, and yet respond very differently to data they haven’t seen before. New work finds this inconsistency to be pervasive.
The same models trained on the same data may show the same performance in the lab, and yet respond very differently to data they haven’t seen before. New work finds this inconsistency to be pervasive.
A neural network learned to read the genes of viruses as though they were text. That could enable researchers to page ahead for potentially dangerous mutations. Researchers at MIT trained a language model to predict mutations that would enable infectious viruses to become even more virulent.
A neural network learned to read the genes of viruses as though they were text. That could enable researchers to page ahead for potentially dangerous mutations. Researchers at MIT trained a language model to predict mutations that would enable infectious viruses to become even more virulent.
Machine learning is helping to design energy cells that charge faster and last longer. Battery developers are using ML algorithms to devise new chemicals, components, and charging techniques faster than traditional techniques allow.
Machine learning is helping to design energy cells that charge faster and last longer. Battery developers are using ML algorithms to devise new chemicals, components, and charging techniques faster than traditional techniques allow.
How does a convolutional neural network recognize a photo of a ski resort? New research shows that it bases its classification on specific neurons that recognize snow, mountains, trees, and houses.
How does a convolutional neural network recognize a photo of a ski resort? New research shows that it bases its classification on specific neurons that recognize snow, mountains, trees, and houses.
Deepfakes have gone mainstream, allowing celebrities to star in commercials without setting foot in a film studio. A new method helps determine whether such endorsements — and other images produced by generative adversarial networks — are authentic.
Deepfakes have gone mainstream, allowing celebrities to star in commercials without setting foot in a film studio. A new method helps determine whether such endorsements — and other images produced by generative adversarial networks — are authentic.
Stay updated with weekly AI News and Insights delivered to your inbox