Profile

Cover photo
monkut h
Lived in chicago
162,734 views
AboutPosts

Stream

monkut h

Shared publicly  - 
 
Trying to understand why dropout networks work so well, I was quite surprised to see that we can get principled uncertainty information from these models for free – without changing a thing.
1 comment on original post
1
Add a comment...

monkut h

Shared publicly  - 
 
 
Fairy Lights in Femtoseconds
Laser technology developed by the Digital Nature Group have developed a small floating hologram which could be used for volumetric graphics or interfaces.
More Here: http://prostheticknowledge.tumblr.com/post/122280842751/fairy-lights-in-femtoseconds-laser-technology
View original post
1
Add a comment...

monkut h

Shared publicly  - 
 
 
Marc Simon Frei Captures Electrical Currents And Tiny Lightning Bolts In His Shocking Photography #ArtTuesday
https://blog.adafruit.com/2015/06/23/marc-simon-frei-captures-electrical-currents-and-tiny-lightning-bolts-in-his-shocking-photography-arttuesday/

Are you ready for some shocking art? Somewhere between science and art, Marc Simon Frei tests their boundaries by combining these two worlds into a stunning series of photographs titled Tesla Sparks. The innovative artist creates electrical currents with a Tesla coil and captures their iridescent glow with his camera.
View original post
2
Add a comment...

monkut h

Shared publicly  - 
 
 
Aww...we had so much fun watching the 6-year-old Samantha explain cosmic rays and demonstrate how to build a homemade cloud chamber to detect them.
Watch this 6 year old explain cosmic rays and demonstrate how to build a homemade cloud chamber to detect them as a fun science project.
2 comments on original post
1
Add a comment...

monkut h

Shared publicly  - 
 
 
Culture defines any business, yet it's also one of the hardest things to manage. In this extract from her TED Book, Margaret Heffernan describes the important, often-overlooked element necessary to...
1 comment on original post
1
Add a comment...

monkut h

Shared publicly  - 
 
 
Have you tried our Artifact Engine? Generate your own futures and start new conversations in your classroom, dinner table, or business meeting today.
View original post
1
Add a comment...

monkut h

Shared publicly  - 
 
 
Algorithmic Music Generation with Recurrent Neural Networks
Algorithmic Music Generation with Recurrent Neural NetworksThere has been a lot of projects popping around the web, employing it invarious areas such as image recognition, playing mario etc … Here,...
View original post
1
Katuhisa Uramoto's profile photo
 
+monkut h +Larry Page +Joichi Ito 

Hypothesis static hundreds more than 100 million of several data cells arbitrarily ties, recognition as a brain, reasoning, doing such as selection, called.
If you look at the neural behavior, no doubt, and, it is reminiscent of, without even necessarily been verified, still unexplored of the earth.
In front approaches that elucidate the mechanism of the brain, we wonder that in the deterministic, it takes much of the time?
In this situation, the opposite approach from the "hypothesis" that has a value.
#kakitaso   is based on the simple assumption, and at the same time prompts the elucidation of brain functions, the results obtained in the process, as appropriate,

k. Uramoto 2015/06/25 9:42(JP)
Add a comment...

monkut h

Shared publicly  - 
 
 
Google's #Inceptionism  work on visualization in ANNs has received a lot of attention recently, and with good reason. But in terms of advancement in Artificial General Intelligence, (AGI) I think the news that more quietly came out of Google's DeepMind lab about Natural Language Processing is much more significant. Here's why:

A massive amount of the human brain is dedicated or related to visual processing - more than half. But it isn't our ability to see that separates humans from the rest of the animal kingdom. That separation was triggered by a much smaller portion of our brain: those small parts dedicated to language.

Human civilization was borne out of language. Language gave us the "self," logic, tools, agriculture, industry, technology and the scientific method. I would argue that language is more fundamental to general intelligence than any other area.

If cracking the AI language nut is a shortcut to general intelligence, we may be arriving there much sooner than we expected. Until now, we haven't had very good data-sets for training NLP ANNs. Karl Moritz Hermann and his colleagues at DeepMind recently realized that they could use the structured data in CNN and Daily Mail articles in order to generate the first large scale structured corpus to date.

Apparently it's paying off:

Teaching machines to read natural language documents remains an elusive challenge. Machine reading systems can be tested on their ability to answer questions posed on the contents of documents that they have seen, but until now large scale training and test datasets have been missing for this type of evaluation. In this work we define a new methodology that resolves this bottleneck and provides large scale supervised reading comprehension data. This allows us to develop a class of attention based deep neural networks that learn to read real documents and answer complex questions with minimal prior knowledge of language structure.

And from the article:

The results clearly show how powerful neural nets have become. Hermann and co say the best neural nets can answer 60 percent of the queries put to them. They suggest that these machines can answer all queries that are structured in a simple way and struggle only with queries that have more complex grammatical structures.
The best way for AI machines to learn is by feeding them huge data sets of annotated examples, and the Daily Mail has unwittingly created one.
11 comments on original post
1
Add a comment...

monkut h

Shared publicly  - 
 
 
Hey all, here's an IPython Notebook with interactive graphs and an explanation of computational methods in Bayesian analysis:

https://plot.ly/ipython-notebooks/computational-bayesian-analysis/
1 comment on original post
1
Add a comment...

monkut h

Shared publicly  - 
 
 
TCP and the lower bound of web performance... is a must watch talk on plumbing, history, and people behind TCP. Awesome.
1 comment on original post
1
Add a comment...
People
Places
Map of the places this user has livedMap of the places this user has livedMap of the places this user has lived
Previously
chicago - tokyo
Links
YouTube
Contributor to
Story
Tagline
'We are all here on earth to help others; what on earth the others are here for, I don’t know' -- John Foster Hall
Introduction
interests? Python, science, and humanity... in that order.
Bragging rights
former renegade BBS sysop
Basic Information
Gender
Male
Other names
monkut