Goto

Collaborating Authors

 superbloom


Superbloom turns Redwood National Park's hills purple

Popular Science

Environment Conservation Land Superbloom turns Redwood National Park's hills purple Riverbank lupine attracts pollinators and shows how prescribed burns can support prairies. More information Adding us as a Preferred Source in Google by using this link indicates that you would like to see more of our content in Google News results. The superbloom about six hours north of San Francisco began in early May. Breakthroughs, discoveries, and DIY tips sent six days a week. Death Valley National Park's ephemeral spring superblooms get most of the attention, but another national park in California has its own impressive floral show this year.


Best superbloom since 2016 fills Death Valley with wildflowers

Popular Science

The colorful explosion of flowers could last through June. Breakthroughs, discoveries, and DIY tips sent six days a week. The driest place on Earth could soon be awash in wildflowers. Death Valley National Park in California is expected to have the best bloom year since 2016. According to the National Park Service, many of their sprouts have not even flowered yet, so the fleeting beauty is just beginning.


Superbloom: Bloom filter meets Transformer

arXiv.org Machine Learning

We extend the idea of word pieces in natural language models to machine learning tasks on opaque ids. This is achieved by applying hash functions to map each id to multiple hash tokens in a much smaller space, similarly to a Bloom filter. We show that by applying a multi-layer Transformer to these Bloom filter digests, we are able to obtain models with high accuracy. They outperform models of a similar size without hashing and, to a large degree, models of a much larger size trained using sampled softmax with the same computational budget. Our key observation is that it is important to use a multi-layer Transformer for Bloom filter digests to remove ambiguity in the hashed input. We believe this provides an alternative method to solving problems with large vocabulary size.