"deep learning" entries

Risto Miikkulainen on evolutionary computation and making robots think for themselves

The O'Reilly Radar Podcast: Evolutionary computation, its applications in deep learning, and how it's inspired by biology.

Subscribe to the O’Reilly Radar Podcast to track the technologies and people that will shape our world in the years to come: Stitcher, TuneIn, iTunes, SoundCloud, RSS

Haeckel_Orchidae

In this week’s episode, David Beyer, principal at Amplify Partners, co-founder of Chart.io, and part of the founding team at Patients Know Best, chats with Risto Miikkulainen, professor of computer science and neuroscience at the University of Texas at Austin. They chat about evolutionary computation, its applications in deep learning, and how it’s inspired by biology.

Finding optimal solutions

We talk about evolutionary computation as a way of solving problems, discovering solutions that are optimal or as good as possible. In these complex domains like, maybe, simulated multi-legged robots that are walking in challenging conditions—a slippery slope or a field with obstacles—there are probably many different solutions that will work. If you run the evolution multiple times, you probably will discover some different solutions. There are many paths of constructing that same solution. You have a population and you have some solution components discovered here and there, so there are many different ways for evolution to run and discover roughly the same kind of a walk, where you may be using three legs to move forward and one to push you up the slope if it’s a slippery slope.

You do (relatively) reliably discover the same solutions, but also, if you run it multiple times, you will discover others. This is also a new direction or recent direction in evolutionary computation—that the standard formulation is that you are running a single run of evolution and you try to, in the end, get the optimum. Everything in the population supports finding that optimum.

Read more…

Comment
Four short links: 11 February 2016

Four short links: 11 February 2016

Surviving Crashes, Thumbs-Up Thumbs-Down Learning, Faster Homomorphic Encryption, and Nerdy V-Day Cards

  1. All File Systems are Not Created Equal: On the Complexity of Crafting Crash Consistent Applications (Paper a Day) — an important subject for me. BOB, the Block Order Breaker, is used to find out what behaviours are exhibited by a number of modern file systems that are relevant to building crash consistent applications. ALICE, the Application Level Intelligent Crash Explorer, is then used to explore the crash recovery behaviour of a number of applications on top of these file systems.
  2. BinaryNet: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1 (Arxiv) — instead of complex positive/negative floating-point weights, this uses +1 and -1 (which I can’t help but think of as “thumbs up”, “thumbs down”) to get nearly state-of-the-art results because a run-time, BinaryNet drastically reduces memory usage and replaces most multiplications by 1-bit exclusive-not-or (XNOR) operations, which might have a big impact on both general-purpose and dedicated Deep Learning hardware. GPLv2 code available.
  3. Microsoft Speeds Up Homomorphic Encryption (The Register) — homomorphic encryption lets databases crunch data without needing keys to decode it.
  4. Nerdy Valentine Cards (Evil Mad Scientist) — for a nerd in your life. (via Cory Doctorow)
Comment
Four short links: 5 February 2016

Four short links: 5 February 2016

Signed Filesystem, Smart Mirror, Deep Learning Tuts, and CLI: Miami

  1. Introducing the Keybase Filesystem — love that crypto is making its way into the filesystem.
  2. DIY Smart Bathroom Mirror — finally, someone is building this science-fiction future! (via BoingBoing)
  3. tensorflow tutorials — for budding deep learners.
  4. clmystery — a command-line murder mystery.
Comment
Four short links: 2 February 2016

Four short links: 2 February 2016

Fourth Industrial Revolution, Agent System, Evidence-Based Programming, and Deep Learning Service

  1. This is Not the Fourth Industrial Revolution (Slate) — the phrase “the fourth Industrial Revolution” has been around for more than 75 years. It first came into popular use in 1940.
  2. Huginn — MIT-licensed system for building agents that perform automated tasks for you online. They can read the Web, watch for events, and take actions on your behalf. Huginn’s Agents create and consume events, propagating them along a directed graph. Think of it as a hackable Yahoo! Pipes plus IFTTT on your own server.
  3. Evidence-Oriented Programming — design programming language syntax and features based on what research shows works. They tested Perl and Java, found apparently not detectably easier to use for novices than a language that my student at the time, Susanna Kiwala (formerly Siebert), created by essentially rolling dice and picking (ridiculous) symbols at random.
  4. Deep Detect — open source deep learning service.
Comment
Four short links: 22 January 2016

Four short links: 22 January 2016

Open Source Ultrasound, Deep Learning MOOC, Corp Dev Translation, and Immersive at Sundance

  1. Murgen — open source open hardware ultrasound.
  2. Udacity Deep Learning MOOC — platform is Google’s TensorFlow.
  3. CorpDev Translation“We’ll continue to follow your progress.” Translation: We’ll reach back out when we see you haven’t raised more money and you are probably more desperate because of your shorter runway.
  4. 8i Take Immersive Tech to Sundance8i’s technology lets filmmakers capture entire performances with off-the-shelf cameras and then place them in pre-existing environments, creating a fully navigable 3-D VR movie that’s far more immersive than the 360-degree videos most have seen.
Comment
Four short links: 8 January 2016

Four short links: 8 January 2016

Modern C, Colorizing Photos, Flashing Toy Drones, and Web + Native

  1. How to C in 2016 — straightforward recommendations for writing C if you have to.
  2. Using Deep Learning to Colorize Old Photos — comes with a trained TensorFlow model to play with.
  3. Open Source Firmware for Toy DronesThe Eachine H8 is a typical-looking mini-quadcopter of the kind that sell for under $20.[…] takes you through a step-by-step guide to re-flashing the device with a custom firmware to enable acrobatics, or simply to tweak the throttle-to-engine-speed mapping for the quad. (via DIY Drones)
  4. Mobile Web vs. Native Apps or Why You Want Both (Luke Wroblewski) — The Web is for audience reach and native apps are for rich experiences. Both are strategic. Both are valuable. So when it comes to mobile, it’s not Web vs. Native. It’s both. The graphs are impressive.
Comment

Patrick Wendell on Spark’s roadmap, Spark R API, and deep learning on the horizon

The O'Reilly Radar Podcast: A special holiday cross-over of the O'Reilly Data Show Podcast.

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

350px-4746439330_f71a44a82f_o

In this special holiday episode of the Radar Podcast, we’re featuring a cross-over of the O’Reilly Data Show Podcast, which you can find on iTunes, Stitcher, TuneIn, or SoundCloud. O’Reilly’s Ben Lorica hosts that podcast, and in this episode, he chats with Apache Spark release manager and Databricks co-founder Patrick Wendell about the roadmap of Spark and where it’s headed, and interesting applications he’s seeing in the growing Spark ecosystem.

Here are some highlights from their chat:

We were really trying to solve research problems, so we were trying to work with the early users of Spark, getting feedback on what issues it had and what types of problems they were trying to solve with Spark, and then use that to influence the roadmap. It was definitely a more informal process, but from the very beginning, we were expressly user driven in the way we thought about building Spark, which is quite different than a lot of other open source projects. … From the beginning, we were focused on empowering other people and building platforms for other developers.

One of the early users was Conviva, a company that does analytics for real-time video distribution. They were a very early user of Spark, they continue to use it today, and a lot of their feedback was incorporated into our roadmap, especially around the types of APIs they wanted to have that would make data processing really simple for them, and of course, performance was a big issue for them very early on because in the business of optimizing real-time video streams, you want to be able to react really quickly when conditions change. … Early on, things like latency and performance were pretty important.

Read more…

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

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