Carnegie Mellon University
Walking the Dog: Training a robot to walk over unsteady terrain with RL.
A reinforcement learning system enabled a four-legged robot to amble over unfamiliar, rapidly changing terrain.
Carnegie Mellon University
3D Scene Synthesis for the Real World: Generating 3D scenes with radiance fields and image data
Researchers have used neural networks to generate novel views of a 3D scene based on existing pictures plus the positions and angles of the cameras that took them. In practice, though, you may not know the precise camera
Carnegie Mellon University
3D Scene Synthesis for the Real World: Generating 3D scenes with radiance fields and image data
Researchers have used neural networks to generate novel views of a 3D scene based on existing pictures plus the positions and angles of the cameras that took them. In practice, though, you may not know the precise camera
Carnegie Mellon University
Unsupervised Prejudice: Image classification models learned bias from ImageNet.
Social biases are well documented in decisions made by supervised models trained on ImageNet’s labels. But they also crept into the output of unsupervised models pretrained on the same dataset.
Carnegie Mellon University
Unsupervised Prejudice: Image classification models learned bias from ImageNet.
Social biases are well documented in decisions made by supervised models trained on ImageNet’s labels. But they also crept into the output of unsupervised models pretrained on the same dataset.
Carnegie Mellon University
Cats Cured of Covid: Why some deep learning models thought cats had 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.
Carnegie Mellon University
Cats Cured of Covid: Why some deep learning models thought cats had 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.
Carnegie Mellon University
Flexible Teachers, Smarter Students: Meta Pseudo Labels improves knowledge distillation.
Human teachers can teach more effectively by adjusting their methods in response to student feedback. It turns out that teacher networks can do the same.
Carnegie Mellon University
Flexible Teachers, Smarter Students: Meta Pseudo Labels improves knowledge distillation.
Human teachers can teach more effectively by adjusting their methods in response to student feedback. It turns out that teacher networks can do the same.
Carnegie Mellon University
Upgrading Softmax: Mixtape is a faster way to avoid the softmax bottleneck.
Softmax commonly computes probabilities in a classifier’s output layer. But softmax isn’t always accurate in complex tasks — say, in a natural-language task, when the length of word vectors is much smaller than the number of words in the vocabulary.
Carnegie Mellon University
Upgrading Softmax: Mixtape is a faster way to avoid the softmax bottleneck.
Softmax commonly computes probabilities in a classifier’s output layer. But softmax isn’t always accurate in complex tasks — say, in a natural-language task, when the length of word vectors is much smaller than the number of words in the vocabulary.
Carnegie Mellon University
Natural Language Processing Models Get Literate: Why 2019 was a breakthrough year for NLP
Earlier language models powered by Word2Vec and GloVe embeddings yielded confused chatbots, grammar tools with middle-school reading comprehension, and not-half-bad translations. The latest generation is so good, some people consider it dangerous.
Carnegie Mellon University
Natural Language Processing Models Get Literate: Why 2019 was a breakthrough year for NLP
Earlier language models powered by Word2Vec and GloVe embeddings yielded confused chatbots, grammar tools with middle-school reading comprehension, and not-half-bad translations. The latest generation is so good, some people consider it dangerous.
Carnegie Mellon University
Self-Training for Sharper Vision: The noisy student method for computer vision, explained
The previous state-of-the-art image classifier was trained on the ImageNet dataset plus 3.5 billion supplemental images from a different database. A new method achieved higher accuracy with one-tenth as many supplemental examples — and they were unlabeled, to boot.
Carnegie Mellon University
Self-Training for Sharper Vision: The noisy student method for computer vision, explained
The previous state-of-the-art image classifier was trained on the ImageNet dataset plus 3.5 billion supplemental images from a different database. A new method achieved higher accuracy with one-tenth as many supplemental examples — and they were unlabeled, to boot.
Subscribe to The Batch
Stay updated with weekly AI News and Insights delivered to your inbox