I only started reading papers this year and have only read two: An empirical study of Rust (found this on 4chan of all places), and a study of local-first software (found right here on HN). The latter truly got me thinking about the cloud services I was using and how your work really isn't yours if it's stored faraway on some cloud servers and not on your local machine. The introduction to Conflict-free Replicated Data Types (CRDTs) was excellent as well.
Ask HN: What's the best paper you've read in 2020?
131–140 of 197 posts
Re: Ask HN: What's the best paper you've read in 2020?
#132Not a paper, but a fantastic talk by Samy Bengio "Towards better understanding generalisation in deep learning" at ASRU2019. Some pretty mind blowing insights - ex: if you replace one layer's weights in a trained classification network with the initialisation weights for the layer (or some intermediate checkpoint as well), many networks show relatively unaffected performance for certain layers ... which is seen as a…
Nice. Love the Bengio Bros. Yoshua especially was right there with Geoffrey Hinton, Yann LeCun, Andrew Ng as the earliest pioneers of successful deep learning, for over 20 years. (While most technologists were crazy about this thing called the World Wide Web in the late 1990's, these guys were shaping brain-inspired AI algorithms and representations.)
Anyways, one of the papers by Yoshua that was really influential on my master's thesis was published in 2009, has received 8956 citations to date on Google Scholar, called "Learning Deep Architectures for AI". For many young researchers, even though this paper pre-dates much of the hyped architectures of the current era, I would still recommend it for its timeless views on deep representations as equivalent to architectural units of learning and knowledge, including its breakdown of deep networks as compositions of functions.
"Learning Deep Architectures for AI" by Yoshua Bengio (2009) - https://www.iro.umontreal.ca/~lisa/pointeurs/TR1312.pdf
Re: Ask HN: What's the best paper you've read in 2020?
#133Awesome robotics paper from Deepmind.
Towards General and Autonomous Learning of Core Skills: A Case Study in Locomotion: https://arxiv.org/abs/2008.12228
Re: Ask HN: What's the best paper you've read in 2020?
#134Not a paper, but a fantastic talk by Samy Bengio "Towards better understanding generalisation in deep learning" at ASRU2019. Some pretty mind blowing insights - ex: if you replace one layer's weights in a trained classification network with the initialisation weights for the layer (or some intermediate checkpoint as well), many networks show relatively unaffected performance for certain layers ... which is seen as a…
Do you know if a video of the talk is available anywhere? I was able to find the slides here: https://www.dropbox.com/sh/4sat5w5exw288zf/AABTC_j9GkRVEChpn...
Re: Ask HN: What's the best paper you've read in 2020?
#135I'm a former biophysicist bumbling my way into distributed systems; was learning rust and bumped into Frank McSherry's blog posts. Thought the Naiad project is really cool! https://cs.stanford.edu/~matei/courses/2015/6.S897/readings/...
But At What COST?!
Re: Ask HN: What's the best paper you've read in 2020?
#136I only properly read the Lottery Ticket Hypothesis paper[1] properly at the start of 2020.
I think it's going to be years before we understand this properly, but in 2020 we are beginning to see practical uses.
At the moment I think it's a toss up: it's either going to be a curiosity that people read, have their mind exploded but can't do anything with or else it's a good chance to be the most influential deep learning paper of the decade.
Re: Ask HN: What's the best paper you've read in 2020?
#137Earlier quoted context omitted.
> But mostly I just love the name. Apparently PNAS had them change it for the final publication, sadly. Big game from an organization with that acronym.
We used to joke in grad school that PNAS stands for Paper Not Accepted in Science.
Yeah they're a real P-NAS.
Re: Ask HN: What's the best paper you've read in 2020?
#138I found this scientific paper interesting, even though it took me a long time to understand the contents.
Molecular repertoire of Deinococcus radiodurans after 1 year of exposure outside the International Space Station within the Tanpopo mission: https://microbiomejournal.biomedcentral.com/articles/10.1186...
Re: Ask HN: What's the best paper you've read in 2020?
#139This Nature paper, Non-invasive early detection of cancer four years before conventional diagnosis using a blood test https://www.nature.com/articles/s41467-020-17316-z Major breakthrough in cell-free diagnostics. The methylation pattern of DNA can be used to identify early-stage cancer, i.e. circulating tumor DNA (ctDNA) has a distinct methylation pattern. The results are based on data from a ten year study which mu…
That's great news!
So now after we know that, what are the treatment options at that stage ?
Re: Ask HN: What's the best paper you've read in 2020?
#140This Nature paper, Non-invasive early detection of cancer four years before conventional diagnosis using a blood test https://www.nature.com/articles/s41467-020-17316-z Major breakthrough in cell-free diagnostics. The methylation pattern of DNA can be used to identify early-stage cancer, i.e. circulating tumor DNA (ctDNA) has a distinct methylation pattern. The results are based on data from a ten year study which mu…
That's great news! So now after we know that, what are the treatment options at that stage ?
Stop eating sugar, and bolster immune system should be first steps.