31 posts tagged with machinelearning.
Displaying 1 through 31 of 31. Subscribe:

Predicting Hearthstone decks

Google researcher Elie Bursztein leads their anti-abuse research team. He sometimes posts articles of extreme interest to game players and computer security people. Such as using machine learning to predict Hearthstone decks: Part 1 - Part 2 - Part 3. His list of publications leads to a wealth of interesting information, for people of various technical inclinations! [more inside]
posted by JHarris on Oct 23, 2016 - 8 comments

Bias Laundering, Fry Oil, Fandom Archivists oh my!

Deep-fried Data (Collections as Data, Library of Congress) For the generation growing up now, the Internet is their window on the world. They take it for granted. It’s only us, who have seen it take shape, and are aware of all the ways it could have been different, who understand that it's fragile, contingent. The coming years will decide to what extent the Internet be a medium for consumption, to what extent it will lift people up, and to what extent it will become a tool of social control.
posted by CrystalDave on Oct 2, 2016 - 16 comments

Auditing Algorithms and Algorithmic Auditing

How big data increases inequality and threatens democracy - "A former academic mathematician and ex-hedge fund quant exposes flaws in how information is used to assess everything from creditworthiness to policing tactics, with results that cause damage both financially and to the fabric of society. Programmed biases and a lack of feedback are among the concerns behind the clever and apt title of Cathy O'Neil's book: Weapons of Math Destruction." [more inside]
posted by kliuless on Sep 6, 2016 - 61 comments

He loves the man that Batman isn’t.

Object Dreams is a blog that catalogs the output of varying text prediction algorithms. Here's part of a Batman: The Animated Series episode it wrote, "The Penguin makes things worse by killing Batman. He has happened to Batman and he is visibly criminal. Batman isn’t still around. Batman is in a cloud. The Penguin finds that he is astounded by killing the man who loves him most. He feels responsible for the death of Gotham’s prominent Batman. He loves the man that Batman isn’t." These programs create Yelp! reviews of the Paris Catacombs, IMDB content warnings, and scripts for Anthony Bourdain's Parts Unknown - among other things. [more inside]
posted by codacorolla on Aug 30, 2016 - 45 comments

I’ve seen things you people wouldn’t believe

Autoencoding Blade Runner — Artist and researcher Terence Broad shows off his results “getting artificial neural networks to reconstruct films — by training them to reconstruct individual frames from films, and then getting them to reconstruct every frame in a given film and resequencing it.” [more inside]
posted by neckro23 on May 25, 2016 - 32 comments

A very complex machine that’s doing nothing very special

Jller is a rock sorting robot built by Prokop Bartoníček & Benjamin Maus. Via Wired Design.
posted by slogger on May 24, 2016 - 31 comments

Datasets over algorithms

"Perhaps the most important news of our day is that datasets — not algorithms — might be the key limiting factor to development of human-level artificial intelligence". Alexander Wissner-Gross responding to Edge. Found here, with some links and a table.
posted by signal on Apr 22, 2016 - 39 comments

Deep Alice

Recently there was a post about using deep learning techniques to apply artistic styles from one image to another. Here is a similar technique applied to moving video from Disney's Alice in Wonderland, using a number of well-known paintings to modify the source. [more inside]
posted by codacorolla on Apr 19, 2016 - 15 comments

Digital Neurons in your Browser

Browser-based Neural Network Demo
What is a Neural Network?
It’s a technique for building a computer program that learns from data. It is based very loosely on how we think the human brain works. First, a collection of software “neurons” are created and connected together, allowing them to send messages to each other. Next, the network is asked to solve a problem, which it attempts to do over and over, each time strengthening the connections that lead to success and diminishing those that lead to failure. [more inside]
posted by CrystalDave on Apr 12, 2016 - 7 comments


Ostagram (github), uses neural networks to combine two images, styling the first (may be NSFW) as the second, with awesome and terrifying results.
posted by dilaudid on Apr 2, 2016 - 70 comments

Digital Humanism

The Digital in the Humanities: An Interview with Franco Moretti - "the term 'digital humanities' (DH) has captured the imagination and the ire of scholars across American universities. The field, which melds computer science with hermeneutics, is championed by supporters as the much-needed means to shake up and expand methods of traditional literary interpretation and is seen by its most outspoken critics as a new fad that symbolizes the neoliberal bean counting destroying American higher education. Somewhere in the middle of these two extremes lies a vast and varied body of work that utilizes and critically examines digital tools in the pursuit of humanistic study. [more inside]
posted by kliuless on Mar 9, 2016 - 21 comments

Werner Herzog has made a documentary about AI and technology

Lo and Behold: Reveries of the Connected World - "With interviewees ranging from Elon Musk to a gaming addict, Werner Herzog presents the web in all its wildness and utopian potential in this dizzying documentary." (via)
posted by kliuless on Jan 26, 2016 - 25 comments

Pepsi Deep Blue

TensorFlow. Google has open-sourced their numerical computation library for machine learning applications. (Especially "deep" learning.) [more inside]
posted by grobstein on Nov 13, 2015 - 28 comments

"About $43,000 a year."

What's the Difference Between Data Science and Statistics?Not long ago, the term "data science" meant nothing to most people-even to those who worked with data. A likely response to the term was: "Isn't that just statistics?" These days, data science is hot. The Harvard Business Review called data scientist the "Sexiest Job of the 21st Century."  So what changed? Why did data science become a distinct term? And what distinguishes data science from statistics?
posted by tonycpsu on Oct 13, 2015 - 38 comments

Where is Google taking us?

I listen to one of the two or three key brains behind the Search algorithm itself, Ben Gomes, who speaks 10 to the dozen of “natural language generation” and “deep learning networks” (and, inevitably, of the “holy grail” of answering users’ questions before they have been asked). [more inside]
posted by Little Dawn on Jul 5, 2015 - 52 comments

"We have not yet developed chair-tossing technology."

Computer science professor Jordan Boyd-Graber is currently working on a National Science Foundation grant for "Bayesian Thinking on Your Feet: Embedding Generative Models in Reinforcement Learning for Sequentially Revealed Data." At first glance, this might not sound like fun, but in the paper, Besting the Quiz Master, Boyd-Graber showed how machine learning could be used to create a quiz bowl version of the Terminator that can take all human comers. This weekend, that proposed machine finally played a nervewracking 200-200 tie game against a team of four Jeopardy! champions (Kristin Sausville of single contestant Final Jeopardy fame, teacher tournament winner Colby Burnett, professional poker player Alex Jacob, and underdog Tournament of Champions winner Ben Ingram).
posted by jonp72 on Jun 5, 2015 - 4 comments


Siri talked only to a few limited functions, like the map, the datebook, and Google. All the imitators, from the outright copies like Google Now and Microsoft's Cortana to a host of more-focused applications with names like Amazon Echo, Samsung S Voice, Evi, and Maluuba, followed the same principle. The problem was you had to code everything. You had to tell the computer what to think. Linking a single function to Siri took months of expensive computer science. You had to anticipate all the possibilities and account for nearly infinite outcomes. If you tried to open that up to the world, other people would just come along and write new rules and everything would get snarled in the inevitable conflicts of competing agendas—just like life. Even the famous supercomputers that beat Kasparov and won Jeopardy! follow those principles. That was the "pain point," the place where everything stops: There were too many rules.
So what if they just wrote rules on how to solve rules?
The idea was audacious. They would be creating a DNA, not a biology, forcing the program to think for itself.
John H. Richardson for Esquire
posted by p3on on Apr 30, 2015 - 68 comments

History as data science

History Lab has "focused on digitizing, structuring and visualizing large sets of declassified US government documents. This is a starting point for showcasing how computational techniques can aid historical research." Can big-data analysis show what kinds of information the government is keeping classified? [more inside]
posted by the man of twists and turns on Apr 27, 2015 - 4 comments

The Shapes of Stories

How many plots are there? Matthew Jockers says six.
posted by the man of twists and turns on Feb 6, 2015 - 61 comments

Embodied Cognition

The Deep Mind of Demis Hassabis - "The big thing is what we call transfer learning. You've mastered one domain of things, how do you abstract that into something that's almost like a library of knowledge that you can now usefully apply in a new domain? That's the key to general knowledge. At the moment, we are good at processing perceptual information and then picking an action based on that. But when it goes to the next level, the concept level, nobody has been able to do that." (previously: 1,2) [more inside]
posted by kliuless on Jan 19, 2015 - 9 comments

Friends With Siri

How Apple’s Siri Became One Autistic Boy's B.F.F. [more inside]
posted by stp123 on Oct 17, 2014 - 40 comments

Essays in English yield information about other languages

Essays and longer texts written in English can provide interesting insights into the linguistic background of the writer, and about the history of other languages, even dying languages, when evaluated by a new computer program developed by a team of computer scientists at MIT and Israel’s Technion. As told on NPR, this discovery came about by accident, when the new program classified someone as Russian when they were Polish, due to the similarity in grammar between the languages. Researchers realized this could allow the program to re-create language families, and could be applied to people who currently may not speak their original language, allowing some categorization of dying languages. More from MIT, and a link to the paper (PDF, from the 2014 Meeting of the Association for Computational Linguistics).
posted by filthy light thief on Oct 1, 2014 - 6 comments

Robot, Heal Thyself

A robot with a broken leg learns to walk again.
posted by tocts on Jul 23, 2014 - 16 comments


A heat map of your preferences over the beer space. Developer Kevin Jamieson writes, "Beer Mapper is a practical implementation of my Active Ranking work on an Apple iPad. The application presents a pair of beers, one pair at a time, from a list of beers that you have indicated you know or have access to and then asks you to select which one you prefer. After you have provided a number of answers, the application shows you a heat map of your preferences over the 'beer space.'" [more inside]
posted by clavicle on Apr 25, 2013 - 58 comments

Find a separating hyperplane with one weird kernel trick!

Pennsylvanians being ripped off by not knowing this one weird kernel trick [more inside]
posted by curuinor on Apr 8, 2013 - 38 comments

Linguistic Time Travel

"The discovery advances UC Berkeley’s mission to make sense of big data and to use new technology to document and maintain endangered languages as critical resources for preserving cultures and knowledge. [...] it can also provide clues to how languages might change years from now."
posted by batmonkey on Feb 11, 2013 - 21 comments

I'll See Your Hand, and Raise You the Future: Computer Learning of Games via Video Input

I See What You Did There: Software Uses Video to Infer Game Rules and Achieve Victory Conditions. A French computer scientist has constructed a system that successfully divines the rules to simple games just by using video input of human players at work.
posted by darth_tedious on Jul 13, 2012 - 15 comments

That's a very nice rendering, Dave.

How do robots see the world? This is an experiment in found machine-vision footage, exploring the aesthetics of the robot eye. [SLVimeo]
posted by jivadravya on Feb 7, 2012 - 14 comments

Simulated Language

In the recent MIT symposium "Brains, Minds and Machines," Chomsky criticized the use of purely statistical methods to understand linguistic behavior. Google's Director of Research, Peter Norvig responds. (via) [more inside]
posted by nangar on May 28, 2011 - 95 comments

80 Million Tiny Images

A visualization of all the nouns in the English language arranged by semantic meaning. [NSFW words included!] [more inside]
posted by carsonb on Jan 15, 2009 - 40 comments

"We were just trying to write songs about prostitutes and lesbians, that's all."

Introduced to Western culture by the Beatles in their single Norwegian Wood, the sitar has featured prominently in North Indian classical music for centuries. Princeton-based computer scientist Ajay Kapur updates the instrument with his ESitar, an audio and video controller that uses gesture input (PDF) and machine learning algorithms to facilitate joining the computer with Ajay in his sitar performance. Undergraduate engineering students at the University of Pennsylvania work from the other direction, building RAVI-bot, an award-winning, self-playing robotic sitar (YouTube) programmed to generate music from classical Raga scales and melodies all on its own. For those in the Philadelphia area, be sure to check out a live performance of RAVI-bot at the local Klein Art Gallery.
posted by Blazecock Pileon on Apr 19, 2007 - 32 comments

Page: 1