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.
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.
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.
Machine learning changes fast. Take natural language processing. Word2vec, introduced in 2013, quickly replaced one-hot encoding with word embeddings. Transformers revolutionized the field in 2017 by parallelizing the previously sequential training process.
Machine learning changes fast. Take natural language processing. Word2vec, introduced in 2013, quickly replaced one-hot encoding with word embeddings. Transformers revolutionized the field in 2017 by parallelizing the previously sequential training process.
In 2021, transformers were harnessed to discover drugs, recognize speech, and paint pictures — and much more.
In 2021, transformers were harnessed to discover drugs, recognize speech, and paint pictures — and much more.
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
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
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.
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.
DeepMind released three papers that push the boundaries — and examine the issues — of large language models.
DeepMind released three papers that push the boundaries — and examine the issues — of large language models.
Transformers have matched or exceeded earlier architectures in language modeling and image classification. New work shows they can achieve state-of-the-art results in some reinforcement learning tasks as well.
Transformers have matched or exceeded earlier architectures in language modeling and image classification. New work shows they can achieve state-of-the-art results in some reinforcement learning tasks as well.
Stay updated with weekly AI News and Insights delivered to your inbox