"machine learning" entries

Four short links: 17 December 2015

Four short links: 17 December 2015

Structured Image Concepts, Google's SDN, Lightbulb DeDRMing, and EFF SF

  1. Visual Genomea data set, a knowledge base, an ongoing effort to connect structured image concepts to language.
  2. Google’s Software Defined Networking[What was the biggest risk you faced rolling out the network? …] we were breaking the fate-sharing principle—which is to say we were putting ourselves in a situation where either the controller could fail without the switch failing, or the switch could fail without the controller failing. That generally leads to big problems in distributed computing, as many people learned the hard way once remote procedure calls became a dominant paradigm.
  3. Philips Backtrack on Lightbulb DRMIn view of the sentiment expressed by our customers, we have decided to reverse the software upgrade so that lights from other brands continue to work as they did before with the Philips Hue system.
  4. Pwning Tomorrow — EFF Publishes SF Anthology. You can expect liberties and freedoms to feature.
Comment
Four short links: 14 December 2015

Four short links: 14 December 2015

Design for the Surveilled, Concept Learning, Media Access, and Programming Challenges

  1. Please Stop Making Secure Messaging Systems — how to design for the surveilled, and the kinds of tools they need BEYOND chat.
  2. Human Level Concept Learning through Probabilistic Program Induction — paper and source code for the nifty “learn handwriting from one example” paper that’s blowing minds.
  3. Access Denied (The Awl) — media had power because they had an audience, but social media gives celebrities, sports people, and politicians a bigger audience than media outlets. So, the media outlets aren’t needed, and consequently, they’re losing “access.” A reporter that depends on access to a compelling subject is by definition a reporter compromised. A publication that depends on cooperation from the world that it specializes in is likewise giving up something in terms of its ability to tell the truth about it. And nearly the entire media as it exists today is built around these negotiations.
  4. Stockfightera series of free, fun programming challenges […] suitable for programmers at all experience levels.
Comment
Four short links: 4 December 2015

Four short links: 4 December 2015

Bacterial Research, Open Source Swift, Deep Forger, and Prudent Crypto Engineering

  1. New Antibiotics Research Direction — most people don’t know that we can’t cultivate and isolate most of the microbes we know about.
  2. Swift now Open Source — Apache v2-licensed. An Apple exec is talking about it and its roadmap.
  3. Deep Forger User Guideclever Twitter bot converting your photos into paintings in the style of famous artists, using deep learning tech.
  4. Prudent Engineering Practice for Cryptographic Protocols (PDF) — paper from the ’90s that is still useful today. Those principles are good for API design too. (via Adrian Colyer)
Comment
Four short links: 27 November 2015

Four short links: 27 November 2015

Android Insecurity, Clear Photos, Speech to Emotion, and Microexpressions from Video

  1. 87% of Android Devices Insecure — researchers find they’re vulnerable to malicious apps because manufacturers have not provided regular security updates. (via Bruce Schneier)
  2. A Computational Approach for Obstruction-Free Photography (Google Research) — take multiple photos from different angles through occlusions like a window with raindrops or reflections, and their software will assemble an unoccluded image. (via Greg Linden)
  3. Algorithms for Affective SensingResults show that the system achieves a six-emotion decision-level correct classification rate of 80% for an acted dataset with clean speech. This PhD thesis is research into algorithm for determining emotion from speech samples, which does so more accurately than humans in a controlled test. (via New Scientist)
  4. Software Learns to Recognise Microexpressions (MIT Technology Review) — Li and co’s machine matched human ability to spot and recognize microexpressions and significantly outperformed humans at the recognition task alone.
Comment

Kristian Hammond on truly democratizing data and the value of AI in the enterprise

The O'Reilly Radar Podcast: Narrative Science's foray into proprietary business data and bridging the data gap.

Subscribe to the O’Reilly Radar Podcast to track the technologies and people that will shape our world in the years to come.

350px-Cognitive_Dissonance_Robert_Couse-Baker

In this week’s episode, O’Reilly’s Mac Slocum chats with Kristian Hammond, Narrative Science’s chief scientist. Hammond talks about Natural Language Generation, Narrative Science’s shift into the world of business data, and evolving beyond the dashboard.

Here are a few highlights:

We’re not telling people what the data are; we’re telling people what has happened in the world through a view of that data. I don’t care what the numbers are; I care about who are my best salespeople, where are my logistical bottlenecks. Quill can do that analysis and then tell you — not make you fight with it, but just tell you — and tell you in a way that is understandable and includes an explanation about why it believes this to be the case. Our focus is entirely, a little bit in media, but almost entirely in proprietary business data, and in particular we really focus on financial services right now.

You can’t make good on that promise [of what big data was supposed to do] unless you communicate it in the right way. People don’t understand charts; they don’t understand graphs; they don’t understand lines on a page. They just don’t. We can’t be angry at them for being human. Instead we should actually have the machine do what it needs to do in order to fill that gap between what it knows and what people need to know.

Read more…

Comment
Four short links: 24 November 2015

Four short links: 24 November 2015

Tabular Data, Distrusting Authority, Data is the Future, and Remote Working Challenges

  1. uitable — cute library for tabular data in console golang programs.
  2. Did Carnegie Mellon Attack Tor for the FBI? (Bruce Schneier) — The behavior of the researchers is reprehensible, but the real issue is that CERT Coordination Center (CERT/CC) has lost its credibility as an honest broker. The researchers discovered this vulnerability and submitted it to CERT. Neither the researchers nor CERT disclosed this vulnerability to the Tor Project. Instead, the researchers apparently used this vulnerability to deanonymize a large number of hidden service visitors and provide the information to the FBI. Does anyone still trust CERT to behave in the Internet’s best interests? Analogous to the CIA organizing a fake vaccination drive to get close to Osama. “Intelligence” agencies.
  3. Google Open-Sourcing TensorFlow Shows AI’s Future is Data not Code (Wired) — something we’ve been saying for a long time.
  4. Challenges of Working Remote (Moishe Lettvin) — the things that make working remote hard aren’t, primarily, logistical; they’re emotional.
Comment
Four short links: 20 November 2015

Four short links: 20 November 2015

Table Mining, Visual Microphones, Platformed Government, and NP-Hard Video Games

  1. DeepDive — Stanford project to create structured data (SQL tables) from unstructured information (text documents) and integrate such data with an existing structured database. DeepDive is used to extract sophisticated relationships between entities and make inferences about facts involving those entities. Code is open source (Apache v2 license). (via Infoworld)
  2. Visual Microphone (MIT) — turn everyday objects — a glass of water, a potted plant, a box of tissues, or a bag of chips — into visual microphones using high-speed photography to detect the small vibrations caused by sound. (via Infoworld)
  3. 10 Rules for Distributed/Networked/Platformed Government (Richard Pope) — Be as vigilant against creating concentrations of power as you are in creating efficiency or bad user experiences. (via Paul Downey)
  4. Classic Nintendo Games are (Computationally) HardWe prove NP-hardness results for five of Nintendo’s largest video game franchises: Mario, Donkey Kong, Legend of Zelda, Metroid, and Pokemon.
Comment

Mike Kuniavsky on the tectonic shift of the IoT

The O'Reilly Radar Podcast: The Internet of Things ecosystem, predictive machine learning superpowers, and deep-seated love for appliances and furniture.

Subscribe to the O’Reilly Radar Podcast to track the technologies and people that will shape our world in the years to come.

350px-Wingate_Sandstone_capping_The_Castle_in_Capitol_Reef_NP

In this week’s episode of the Radar Podcast, O’Reilly’s Mary Treseler chats with Mike Kuniavsky, a principal scientist in the Innovation Services Group at PARC. Kuniavsky talks about designing for the Internet of Things ecosystem and why the most interesting thing about the IoT isn’t the “things” but the sensors. He also talks about his deep-seated love for appliances and furniture, and how intelligence will affect those industries.

Here are some highlights from their conversation:

Wearables as a class is really weird. It describes where the thing is, not what it is. It’s like referring to kitchenables. ‘Oh, I’m making a kitchenable.’ What does that mean? What does it do for you?

There’s this slippery slope between service design and UX design. I think UX design is more digital and service design allows itself to include things like a poster that’s on a wall in a lobby, or a little card that gets mailed to people, or a human being that they can talk to. … Service design takes a slightly broader view, whereas UX design is — and I think usefully — still focused largely on the digital aspect of it.

Read more…

Comment
Four short links: 18 November 2015

Four short links: 18 November 2015

Crypto Comms, Science Funding, Geo DB, and AI Ambitions

  1. If The Paris Hackers Weren’t Using Crypto, The Next Ones Will (Cory Doctorow) — But the reality is that criminals will be using crypto soon, if they aren’t already, for the same reason they’re using computers. Using crypto is the best way to communicate.
  2. Google $50M Heart Disease Effort — instead of taking bids for $250K chunks of the money, they will fund one team for five years. Applications close Feb 14.
  3. Pyro (Usenix) — This paper presents Pyro, a spatial-temporal big data storage system tailored for high-resolution geometry queries and dynamic hotspots. Pyro understands geometries internally, which allows range scans of a geometry query to be aggregately optimized. Moreover, Pyro employs a novel replica placement policy in the DFS layer that allows Pyro to split a region without losing data locality benefits.
  4. Inside Mark Zuckerberg’s Bold Plan for Facebook (FastCompany) — “One of our goals for the next five to 10 years,” Zuckerberg tells me, “is to basically get better than human level at all of the primary human senses: vision, hearing, language, general cognition.”
Comment
Four short links: 17 November 2015

Four short links: 17 November 2015

Remix Contest, Uber Asymmetry, Language Learning, and Continuous Delivery

  1. GIF It Up — very clever remix campaign to use heritage content—Friday is your last day to enter this year’s contest, so get creating! My favourite.
  2. Uber’s Drivers: Information Asymmetries and Control in Dynamic WorkOur conclusions are two-fold: first, that the information asymmetries produced by Uber’s system are fundamental to its ability to structure indirect control over its workers; and second, that Uber relies heavily on the evolving rhetoric of the algorithm to justify these information asymmetries to drivers, riders, as well as regulators and outlets of public opinion.
  3. ANNABELL — unsupervised language learning using artificial neural networks, install your own four year old. The paper explains how.
  4. Spinnakeran open source, multi-cloud continuous delivery platform for releasing software changes with high velocity and confidence.
Comment