"machine learning" entries

Four short links: 29 September 2014

Four short links: 29 September 2014

Feedback Surprises, Ownership Changes, Teaching Lessons, and 3D Retail

  1. How Community Feedback Shapes Behaviour (PDF) — Not only do authors of negatively-evaluated content contribute more, but also their future posts are of lower quality, and are perceived by the community as such. Moreover, these authors are more likely to subsequently evaluate their fellow users negatively, percolating these effects through the community. In contrast, positive feedback does not carry similar effects, and neither encourages rewarded authors to write more, nor improves the quality of their posts. Interestingly, the authors that receive no feedback are most likely to leave a community. Furthermore, a structural analysis of the voter network reveals that evaluations polarize the community the most when positive and negative votes are equally split.
  2. When Everything Works Like Your Cell Phone (The Atlantic) — our relationship to ownership is about to undergo a wild transformation.
  3. Teaching Me Softly — article of anecdotes drawing parallels between case studies in machine learning and things we know about human learning.
  4. SuperAwesome Me (3D Print) — Walmart to install 3d scanning booths and 3d printers so you can put your own head on a Hasbro action figure. Hasbro have the religion: they also paired with Shapeways for superfanart.com. (via John Battelle)
Comment
Four short links: 26 September 2014

Four short links: 26 September 2014

Good Communities, AI Games, Design Process, and Web Server Library

  1. 15 Lessons from 15 Years of Blogging (Anil Dash) — If your comments are full of assholes, it’s your fault. Good communities don’t just happen by accident.
  2. Replicating DeepMind — open source attempt to build deep learning network that can play Atari games. (via RoboHub)
  3. ToyTalk — fantastic iterative design process for the product (see the heading “A Bit of Trickery”)
  4. h2oan optimized HTTP server implementation that can be used either as a standalone server or a library.
Comment
Four short links: 19 September 2014

Four short links: 19 September 2014

Deep Learning Bibliography, Go Playground, Tweet-a-Program, and Memory Management

  1. Deep Learning Bibliographyan annotated bibliography of recent publications (2014-) related to Deep Learning.
  2. Inside the Go Playground — on safely offering a REPL over the web to strangers.
  3. Wolfram Tweet-a-Program — clever marketing trick, and reminiscent of Perl Golf-style “how much can you fit into how little” contests.
  4. Memory Management Reference — almost all you ever wanted to know about memory management.
Comment
Four short links: 15 September 2014

Four short links: 15 September 2014

Weird Machines, Libraries May Scan, Causal Effects, and Crappy Dashboards

  1. The Care and Feeding of Weird Machines Found in Executable Metadata (YouTube) — talk from 29th Chaos Communication Congress, on using tricking the ELF linker/loader into arbitrary computation from the metadata supplied. Yes, there’s a brainfuck compiler that turns code into metadata which is then, through a supernatural mix of pixies, steam engines, and binary, executed. This will make your brain leak. Weird machines are everywhere.
  2. European Libraries May Digitise Books Without Permission“The right of libraries to communicate, by dedicated terminals, the works they hold in their collections would risk being rendered largely meaningless, or indeed ineffective, if they did not have an ancillary right to digitize the works in question,” the court said. Even if the rights holder offers a library the possibility of licensing his works on appropriate terms, the library can use the exception to publish works on electronic terminals, the court ruled. “Otherwise, the library could not realize its core mission or promote the public interest in promoting research and private study,” it said.
  3. CausalImpact (GitHub) — Google’s R package for estimating the causal effect of a designed intervention on a time series. (via Google Open Source Blog)
  4. Laws of Crappy Dashboards — (caution, NSFW language … “crappy” is my paraphrase) so true. Not talking to users will result in a [crappy] dashboard. You don’t know if the dashboard is going to be useful. But you don’t talk to the users to figure it out. Or you just show it to them for a minute (with someone else’s data), never giving them a chance to figure out what the hell they could do with it if you gave it to them.
Comment: 1
Four short links: 12 September 2014

Four short links: 12 September 2014

Knowledge Graphs, Multi-Language Declarations, Monitoring, and More Monitoring

  1. Google Knowledge Vault and Topic Modeling — recap of talks by Google and Facebook staff about how they use their knowledge graphs. I found this super-interesting.
  2. djinniA tool for generating cross-language type declarations and interface bindings.
  3. monita small Open Source utility for managing and monitoring Unix systems. Monit conducts automatic maintenance and repair and can execute meaningful causal actions in error situations.
  4. perf-toolingList of performance analysis, monitoring and optimization tools.
Comments: 3
Four short links: 1 September 2014

Four short links: 1 September 2014

Sibyl, Bitrot, Estimation, and ssh

  1. Sibyl: Google’s System for Large Scale Machine Learning (YouTube) — keynote at DSN2014 acting as an intro to Sibyl. (via KD Nuggets)
  2. Bitrot from 1997That’s 205 failures, an actual link rot figure of 91%, not 57%. That leaves only 21 URLs as 200 OK and containing effectively the same content.
  3. What We Do And Don’t Know About Software Effort Estimation — nice rundown of research in the field.
  4. fabric — simple yet powerful ssh library for Python.
Comment: 1
Four short links: 27 August 2014

Four short links: 27 August 2014

Discourse 1.0, Programmable Matter, Versioned Databases, and What Humans Learned About Machine Learning

  1. Discourse turns 1.0 — community/forum software that doesn’t suck.
  2. Programmable Matter (IEEE Spectrum) — recap of where research is going in this area.
  3. Liquibasesource control for your database. Apache 2.0 licensed.
  4. A Few Useful Things to Know About Machine Learning (PDF) — This article summarizes twelve key lessons that machine learning researchers and practitioners have learned. These include pitfalls to avoid, important issues to focus on, and answers to common questions. My fave: First-timers are often surprised by how little time in a machine learning project is spent actually doing machine learning. But it makes sense if you consider how time-consuming it is to gather data, integrate it, clean it and pre-process it, and how much trial and error can go into feature design.
Comments: 2
Four short links: 20 August 2014

Four short links: 20 August 2014

Plant Properties, MQ Comparisons, 1915 Vis, and Mobile Web Weaknesses

  1. Machine Learning for Plant Properties — startup building database of plant genomics, properties, research, etc. for mining. The more familiar you are with your data and its meaning, the better your machine learning will be at suggesting fruitful lines of query … and the more valuable your startup will be.
  2. Dissecting Message Queues — throughput, latency, and qualitative comparison of different message queues. MQs are to modern distributed architectures what function calls were to historic unibox architectures.
  3. 1915 Data Visualization Rules — a reminder that data visualization is not new, but research into effectiveness of alternative presentation styles is.
  4. The Broken Promise of the Mobile Webit’s not just about the UI – it’s also about integration with the mobile device.
Comment
Four short links: 7 August 2014

Four short links: 7 August 2014

Material Design, Stewart's Slack, Sketching in Javascript, and Neural Networks and Deep Learning

  1. Material Design in the Google I/O App (Medium) — steps through design thinking as they put Google’s new design metaphor in place. I’ve been chewing on material design. It brings an internal consistency and logic to the Android world that Apple’s iOS and OS X visual worlds have been losing over the years. How long until web users expect this consistency too?
  2. Stewart and Slack (Wired) — profile of Foo Stewart Butterfield and his shiny Slack startup.
  3. p5js — a new Processing-inspired code-as-sketching in Javascript. Using the original metaphor of a software sketchbook, p5.js has a full set of drawing functionality. However, you’re not limited to your drawing canvas, you can think of your whole browser page as your sketch!
  4. Neural Networks and Deep Learning — a free online book to teach you … well, neural networks and deep learning.
Comment
Four short links: 24 July 2014

Four short links: 24 July 2014

Neglected ML, Crowdfunded Recognition, Debating Watson, and Versioned p2p File System

  1. Neglected Machine Learning IdeasPerhaps my list is a “send me review articles and book suggestions” cry for help, but perhaps it is useful to others as an overview of neat things.
  2. First Crowdfunded Book on Booker Shortlist — Booker excludes self-published works, but “The Wake” was through Unbound, a Threadless-style “if we hit this limit, the book is printed and you have bought a copy” site.
  3. Watson Can Debate Its Opponents (io9) — Speaking in nearly perfect English, Watson/The Debater replied: “Scanned approximately 4 million Wikipedia articles, returning ten most relevant articles. Scanned all 3,000 sentences in top ten articles. Detected sentences which contain candidate claims. Identified borders of candidate claims. Assessed pro and con polarity of candidate claims. Constructed demo speech with top claim predictions. Ready to deliver.”
  4. ipfsa global, versioned, peer-to-peer file system. It combines good ideas from Git, BitTorrent, Kademlia, and SFS. You can think of it like a single BitTorrent swarm, exchanging Git objects, making up the web. IPFS provides an interface much simpler than HTTP, but has permanence built in.. (via Sourcegraph)
Comment