XNOR-Net

ImageNet classification using binary Convolutional Neural Networks

Explore on GitHub Read Hacker News discussions

2Distinct people

2Mentions

0Explicit recommenders

874GitHub stars

REPOSITORY AT A GLANCE

What to know before exploring

What it is

ImageNet classification using binary Convolutional Neural Networks

GitHub

Where it is used

No documented product use has been verified yet.

What people are saying

No recommendation phrase was found in the indexed comments.

No classified warning is attached to this page. Read the discussions before treating silence as approval.

Also in these discussions

No other repository is repeatedly linked in the same discussions.

This week on Hacker News

Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 5:04:57 PM UTC.

No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.

Mentions over time

HN mentions by hour2 dated mentions

Observed mentions: 2017-01-23 00:22:41 UTC to 2017-01-23 04:40:13 UTC.

Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.

View mention counts and date ranges

UTC ranges include their start and exclude their end. Select a period to filter the source evidence.
Period	Start (UTC)	End (exclusive, UTC)	Mentions	Comments
Jan 23, 00:00	2017-01-23 00:00:00 UTC	2017-01-23 01:00:00 UTC	1	1
Jan 23, 01:00	2017-01-23 01:00:00 UTC	2017-01-23 02:00:00 UTC	0	0
Jan 23, 02:00	2017-01-23 02:00:00 UTC	2017-01-23 03:00:00 UTC	0	0
Jan 23, 03:00	2017-01-23 03:00:00 UTC	2017-01-23 04:00:00 UTC	0	0
Jan 23, 04:00	2017-01-23 04:00:00 UTC	2017-01-23 05:00:00 UTC	1	1

What Hacker News says

2 sources

emcq·Jan 23, 2017

This is for optimizing inference. For consumer devices such as smart cameras, speech recognition on your phone, or robotics that's the part that matters. They have real speed improvements by using 1-bit quantitzed weights and then running operations using 32-bit or 64-bit bitfields which happen to use very few instructions/cycles on modern CPUS: https://github.com/allenai/XNOR-Net

In XNOR.ai frees AI from the prison of the supercomputer

shpx·Jan 23, 2017

I think this is their paper http://www.arxiv-sanity.com/1603.05279 and this is the (torch) code https://github.com/allenai/XNOR-Net Cursory look suggests they quantize both the weights and functions during classification on the smart phone and during the forwards and backwards pass during training. But you still have to use a continuous version of your logic gate to get an error gradient during training, so I'm guessing they still do the training on "supercomputers" (a desktop with a gpu really).

In XNOR.ai frees AI from the prison of the supercomputer