- Google’s Seven Robotics Companies (IEEE) — The seven companies are capable of creating technologies needed to build a mobile, dexterous robot. Mr. Rubin said he was pursuing additional acquisitions. Rundown of those seven companies.
- Hebel (Github) — GPU-Accelerated Deep Learning Library in Python.
- What We Learned Open Sourcing — my eye was caught by the way they offered APIs to closed source code, found and solved performance problems, then open sourced the fixed code.
ENTRIES TAGGED "deep learning"
Flexible Data, Google's Bottery, GPU Assist Deep Learning, and Open Sourcing
Internet Cities, Defying Google Glass, Deep Learning Book, and Open Paleoanthropology
- The Death and Life of Great Internet Cities — “The sense that you were given some space on the Internet, and allowed to do anything you wanted to in that space, it’s completely gone from these new social sites,” said Scott. “Like prisoners, or livestock, or anybody locked in institution, I am sure the residents of these new places don’t even notice the walls anymore.”
- What You’re Not Supposed To Do With Google Glass (Esquire) — Maybe I can put these interruptions to good use. I once read that in ancient Rome, when a general came home victorious, they’d throw him a triumphal parade. But there was always a slave who walked behind the general, whispering in his ear to keep him humble. “You are mortal,” the slave would say. I’ve always wanted a modern nonslave version of this — a way to remind myself to keep perspective. And Glass seemed the first gadget that would allow me to do that. In the morning, I schedule a series of messages to e-mail myself throughout the day. “You are mortal.” “You are going to die someday.” “Stop being a selfish bastard and think about others.” (via BoingBoing)
- Neural Networks and Deep Learning — Chapter 1 up and free, and there’s an IndieGogo campaign to fund the rest.
- What We Know and Don’t Know — That highly controlled approach creates the misconception that fossils come out of the ground with labels attached. Or worse, that discovery comes from cloaked geniuses instead of open discussion. We’re hoping to combat these misconceptions by pursuing an open approach. This is today’s evolutionary science, not the science of fifty years ago We’re here sharing science. [...] Science isn’t the answers, science is the process. Open science in paleoanthropology.
IP Woe, Deep Learning Intro, Rapid Prototyping Bots, 3D Display
- TPPA Trades Away Internet Freedoms (EFF) — commentary on the wikileaked text of the trade agreement.
- Deep Learning 101 — introduction to the machine learning trend of choice.
- Large Scale Rapid Prototyping Robots — an informal list of large rapid prototyping systems [...] including: big 3-axis systems that print plastic, sand, or cement; large robot arms with extruders and milling bits; and large industrial arms for bending metal and assembling modular structures.
- Dynamic Shape Display (MIT) — a Dynamic Shape Display that can render 3D content physically, so users can interact with digital information in a tangible way. inFORM can also interact with the physical world around it, for example moving objects on the table’s surface. (via Fast Company)
Google Code Analysis, Deep Learning, Front-End Workflow, and SICP in JS
- Steve Yegge on GROK (YouTube) — The Grok Project is an internal Google initiative to simplify the navigation and querying of very large program source repositories. We have designed and implemented a language-neutral, canonical representation for source code and compiler metadata. Our data production pipeline runs compiler clusters over all Google’s code and third-party code, extracting syntactic and semantic information. The data is then indexed and served to a wide variety of clients with specialized needs. The entire ecosystem is evolving into an extensible platform that permits languages, tools, clients and build systems to interoperate in well-defined, standardized protocols.
- Deep Learning for Semantic Analysis — When trained on the new treebank, this model outperforms all previous methods on several metrics. It pushes the state of the art in single sentence positive/negative classification from 80% up to 85.4%. The accuracy of predicting fine-grained sentiment labels for all phrases reaches 80.7%, an improvement of 9.7% over bag of features baselines. Lastly, it is the only model that can accurately capture the effect of contrastive conjunctions as well as negation and its scope at various tree levels for both positive and negative phrases.
- Fireshell — workflow tools and framework for front-end developers.
Eleven areas of focus for deeper investigation.
Deep Learning, Internet of ux Nightmares, Mozilla Science Lab, and Ground-Up Computing
- Weekend Reads on Deep Learning (Alex Dong) — an article and two videos unpacking “deep learning” such as multilayer neural networks.
- The Internet of Actual Things — “I have 10 reliable activations remaining,” your bulb will report via some ridiculous light-bulbs app on your phone. “Now just nine. Remember me when I’m gone.” (via Andy Baio)
- Announcing the Mozilla Science Lab (Kaitlin Thaney) — We also want to find ways of supporting and innovating with the research community – building bridges between projects, running experiments of our own, and building community. We have an initial idea of where to start, but want to start an open dialogue to figure out together how to best do that, and where we can be of most value..
- NAND to Tetris — The site contains all the software tools and project materials necessary to build a general-purpose computer system from the ground up. We also provide a set of lectures designed to support a typical course on the subject. (via Hacker News)
Distributed Browser-Based Computation, Streaming Regex, Preventing SQL Injections, and SVM for Faster Deep Learning
- WeevilScout — browser app that turns your browser into a worker for distributed computation tasks. See the poster (PDF). (via Ben Lorica)
- sregex (Github) — A non-backtracking regex engine library for large data streams. See also slide notes from a YAPC::NA talk. (via Ivan Ristic)
- Bobby Tables — a guide to preventing SQL injections. (via Andy Lester)
- Deep Learning Using Support Vector Machines (Arxiv) — we are proposing to train all layers of the deep networks by backpropagating gradients through the top level SVM, learning features of all layers. Our experiments show that simply replacing softmax with linear SVMs gives significant gains on datasets MNIST, CIFAR-10, and the ICML 2013 Representation Learning Workshop’s face expression recognition challenge. (via Oliver Grisel)