Understanding Deep Learning requires rethinking generalization
Very entertaining article which could be viewed either as philosophical discoveries, or as "machine learning specialists rediscover information theory" :)
https://arxiv.org/abs/1611.03530
Very entertaining article which could be viewed either as philosophical discoveries, or as "machine learning specialists rediscover information theory" :)
https://arxiv.org/abs/1611.03530
cyberpunk is already there. also, cryptocoins are slowly but steadily expanding the market for formal verification methods, which is a good thing.
https://zcoin.io/language/en/important-announcement-zerocoin-implementation-bug/
https://zcoin.io/language/en/important-announcement-zerocoin-implementation-bug/
firo.org
Home | Firo - Privacy-preserving cryptocurrency
Firo is a digital currency with a focus on setting privacy standards.
Limits of psychology, specified in machine learning terms
https://jsteinhardt.wordpress.com/2017/02/07/model-mis-specification-and-inverse-reinforcement-learning/
https://jsteinhardt.wordpress.com/2017/02/07/model-mis-specification-and-inverse-reinforcement-learning/
Academically Interesting
Model Mis-specification and Inverse Reinforcement Learning
In my previous post, “Latent Variables and Model Mis-specification”, I argued that while machine learning is good at optimizing accuracy on observed signals, it has less to say about correctly infe…
Interpreters are cool, but interpreters need parsers
http://jeffreykegler.github.io/Ocean-of-Awareness-blog/individual/2013/03/interpreter.html
http://jeffreykegler.github.io/Ocean-of-Awareness-blog/individual/2013/03/interpreter.html
Magic: the Gathering is Turing Complete
http://www.toothycat.net/~hologram/Turing/index.html
http://www.toothycat.net/~hologram/Turing/index.html
A Theory of Memory Models [concurrency, not ML]
http://saraswat.org/raofull.pdf
http://saraswat.org/raofull.pdf
The Origin of Time In Conscious Agents [Donald Hoffman, 2014]
http://cogsci.uci.edu/~ddhoff/HoffmanTime.pdf
http://cogsci.uci.edu/~ddhoff/HoffmanTime.pdf
Curated list of falsehoods programmers believe in.
https://github.com/kdeldycke/awesome-falsehood
https://github.com/kdeldycke/awesome-falsehood
GitHub
GitHub - kdeldycke/awesome-falsehood: 😱 Falsehoods Programmers Believe in
😱 Falsehoods Programmers Believe in. Contribute to kdeldycke/awesome-falsehood development by creating an account on GitHub.
#fail CloudBleed: CloudFlare proxies leak your traffic into random HTTP responses, into search engines and so on
https://news.ycombinator.com/item?id=13718752
https://news.ycombinator.com/item?id=13718752
Both Julia and Scala people are trying to generalize numeric types. Julia approach can be found in the docs and issues on the compiler itself, and Scala approach is a library:
https://github.com/non/spire
https://github.com/non/spire
GitHub
non/spire
Powerful new number types and numeric abstractions for Scala. - non/spire
data modeling/warehousing tips are always in short supply
http://ehealthafrica.github.io/couchdb-best-practices/
http://ehealthafrica.github.io/couchdb-best-practices/
ehealthafrica.github.io
CouchDB Best Practices
collect best practices around the CouchDB universe.
TLDR: Technology in search for a problem is not a product.
http://www.bradfordcross.com/blog/2017/3/3/five-ai-startup-predictions-for-2017
http://www.bradfordcross.com/blog/2017/3/3/five-ai-startup-predictions-for-2017
Bradford Cross
Five AI Startup Predictions for 2017
Bots go bust Deep learning goes commodity AI is cleantech 2.0 for VCs MLaaS dies a second death Full stack vertical AI startups actually work With AI in a full-fledged mania, 2017 will be the year of reckoning. Pure hype trends will…
CIA Hacking Tools Leak (looks too polished though)
https://wikileaks.org/ciav7p1/index.html
https://wikileaks.org/ciav7p1/index.html
#gamedev #cg Hashed and Stochastic Alpha-Testing (I3D '17)
http://cwyman.org/papers/i3d17_hashedAlpha.pdf
http://cwyman.org/papers/i3d17_hashedAlpha.pdf
Fast, simple and unbiased importance sampling (Baker '87)
https://en.wikipedia.org/wiki/Stochastic_universal_sampling
https://en.wikipedia.org/wiki/Stochastic_universal_sampling
Wikipedia
Stochastic universal sampling
data sampling technique used in genetic algorithm
Making Least-Squares estimation robust using iterative reweighting
https://www.sebastiansylvan.com/post/robustestimation/
https://www.sebastiansylvan.com/post/robustestimation/
New tools show that neurons are more complicated than previously thought
https://doi.org/10.1126/science.aaj1497
https://doi.org/10.1126/science.aaj1497
Science
Dynamics of cortical dendritic membrane potential and spikes in freely behaving rats
Neural activity in vivo is primarily measured using extracellular somatic spikes, which provide limited information about neural computation. Hence, it is necessary to record from neuronal dendrites, which generate dendritic action potentials (DAP) and profoundly…