Viewing profile — noahgolmant
noahgolmant
HN member- Joined
- Fri, Feb 05, 2021, 6:56 PM UTC
- HN karma
- 46
- Public activity
- 12 items
- HN profile
- View on Hacker News ↗
About noahgolmant
No profile information was provided.
Recent public activity
- story
- story
-
comment
Comment #48175590
There is some literature on student-teacher training with Jacobian matching: https://arxiv.org/abs/1803.00443 this might be in the direction you're looking for. I believe in the cr…
-
comment
Comment #48132233
Back in 2018 I published pytorch-hessian-eigenthings, a niche open source package for GPU-accelerated curvature analysis of PyTorch models. Loss landscape curvature metrics like th…
- story
-
comment
Comment #48054506
The human has unique context. They may work in a niche domain or they talked to people and observed an unsolved problem. Then they express a potential solution via OSS. It's like p…
-
comment
Comment #48054392
I don't really know. Certainly we need a higher bar. The Kafka example in the post may be hyperbolic but I agree it pollutes the space. But we also can't swing the other way and re…
-
comment
Comment #48053845
There has to be room for an AI-driven project that expresses a unique idea, even if there's no community around it yet. Someone has to express it, and from now on that idea will la…
-
comment
Comment #47982229
I would not extrapolate California results to the rest of the country. Other regions like Northern Virginia or Dallas-Forth Worth dominate current and future data center load. They…
-
comment
Comment #47630482
You may want to look into the PMTiles format and tippecanoe. It efficiently produces pyramidal XYZ tile overviews of vector data. Sometimes this is also done server side via the Po…
-
story
Show HN: Build ML training datasets from large-scale satellite/aerial imagery
This is a small tool to label bounding boxes on satellite/aerial imagery and export training datasets for object detection. Web maps like Google Earth work by stitching together lo…
-
comment
Comment #46266828
A tool to build labeled object detection training datasets from large-scale satellite/aerial imagery collections: https://github.com/noahgolmant/label-tiles Web maps usually join t…