Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Lingle, Lucas"'
Autor:
Lingle, Lucas
Large artificial neural networks have become a mainstay of language, vision, and audio processing and synthesis, yet their initializations and learning rates are often set in an unsophisticated fashion, due to the high cost of hyperparameter sweeps a
Externí odkaz:
http://arxiv.org/abs/2404.05728
Autor:
Lingle, Lucas D.
We introduce Transformer-VQ, a decoder-only transformer computing softmax-based dense self-attention in linear time. Transformer-VQ's efficient attention is enabled by vector-quantized keys and a novel caching mechanism. In our large-scale experiment
Externí odkaz:
http://arxiv.org/abs/2309.16354
Autor:
Lingle, Lucas D.
The field of meta-learning seeks to improve the ability of today's machine learning systems to adapt efficiently to small amounts of data. Typically this is accomplished by training a system with a parametrized update rule to improve a task-relevant
Externí odkaz:
http://arxiv.org/abs/2103.02265