Timezone: »

Riptide: Fast End-to-End Binarized Neural Networks
Joshua Fromm · Meghan Cowan · Matthai Philipose · Luis Ceze · Shwetak Patel

Mon Mar 02 04:30 PM -- 07:00 PM (PST) @ Ballroom A #29

Binarized neural networks have attracted much recent attention due to their promise of making convolutional neural networks fast and compact. However, these benefits have proven hard to realize in practice. In this paper, we identify the underlying barriers to high performance and propose solutions from missing implementations for certain operations to carefully scheduled library support for binarized linear algebra operations. The combination of these innovations allows us to report the first measured end-to-end speedups for binarized networks. For instance, we show a 6.3_ speedup over a standard VGGNet variant at state-of-the-art (64.2% for top-1 binarized classification of ImageNet) accuracy. More broadly speedups range from 4-12_ and the techniques we propose are crucial to achieving them.

Author Information

Joshua Fromm (University of Washington)
Meghan Cowan (University of Washington)
Matthai Philipose (Microsoft Research)
Luis Ceze (University of Washington and OctoML)
Shwetak Patel (University of Washington)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors