Transformer networks have revolutionized natural language processing, but they hog processor cycles and memory. New research demonstrates a more frugal variation.
Geoffrey Hinton, Yoshua Bengio, and Yann LeCun presented their latest thinking about deep learning’s limitations and how to overcome them.
Geoffrey Hinton, Yoshua Bengio, and Yann LeCun presented their latest thinking about deep learning’s limitations and how to overcome them.
Androids may not dream of electric sheep, but some crack jokes about horses and cows. Meena, a 2.6-billion parameter chatbot developed by Google Brain, showed impressive conversational ability, discussing a variety of topics.
Androids may not dream of electric sheep, but some crack jokes about horses and cows. Meena, a 2.6-billion parameter chatbot developed by Google Brain, showed impressive conversational ability, discussing a variety of topics.
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.
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.
Computer vision has potential to spot cancer earlier and more accurately than human experts. A new system surpassed human accuracy in trials, but critics aren’t convinced.
Researchers aiming to increase accuracy in object detection generally enlarge the network, but that approach also boosts computational cost. A novel architecture sets a new state of the art in accuracy while cutting the compute cycles required.
Researchers aiming to increase accuracy in object detection generally enlarge the network, but that approach also boosts computational cost. A novel architecture sets a new state of the art in accuracy while cutting the compute cycles required.
Computer vision has potential to spot cancer earlier and more accurately than human experts. A new system surpassed human accuracy in trials, but critics aren’t convinced.
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.
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.
As language models show increasing power, a parallel trend has received less notice: The vogue for naming models after characters in the children’s TV show Sesame Street.
As language models show increasing power, a parallel trend has received less notice: The vogue for naming models after characters in the children’s TV show Sesame Street.
Stay updated with weekly AI News and Insights delivered to your inbox