Entries from November 2016 ↓

[1611.04558] Google’s Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation
We propose a simple, elegant solution to use a single Neural Machine Translation (NMT) model to translate between multiple languages. Our solution requires no change in the model architecture from our base system but instead introduces an artificial token at the beginning of the input sentence to specify the required target language. The rest of the model, which includes encoder, decoder and attention, remains unchanged and is shared across all languages. Using a shared wordpiece vocabulary, our approach enables Multilingual NMT using a single model without any increase in parameters, which is significantly simpler than previous proposals for Multilingual NMT. Our method often improves the translation quality of all involved language pairs, even while keeping the total number of model parameters constant. On the WMT’14 benchmarks, a single multilingual model achieves comparable performance for English→French and surpasses state-of-the-art results for English→German. Similarly, a single multilingual model surpasses state-of-the-art results for French→English and German→English on WMT’14 and WMT’15 benchmarks respectively. On production corpora, multilingual models of up to twelve language pairs allow for better translation of many individual pairs. In addition to improving the translation quality of language pairs that the model was trained with, our models can also learn to perform implicit bridging between language pairs never seen explicitly during training, showing that transfer learning and zero-shot translation is possible for neural translation. Finally, we show analyses that hints at a universal interlingua representation in our models and show some interesting examples when mixing languages.
ProPublica
Fake News Onslaught Targets Pizzeria as Nest of Child-Trafficking – NYTimes.com
Experts Urge Hillary Clinton to Challenge Election Results
Google’s AI translation tool seems to have invented its own secret internal language | TechCrunch
GitHub – googleapis/openapi-compiler: Compile OpenAPI specifications into equivalent Protocol Buffer representations
trace – GoDoc
Now I’m tracing everything. The Stackdriver Trace Go package makes it too easy. https://godoc.org/cloud.google.com/go/trace https://twitter.com/kelseyhightower/status/801222046633988096/photo/1
Twitter
RT @nycsouthpaw: Most interesting item in the Trump Fdn’s 2015 filing, imo: A $150,000 contribution from the fdn of Ukrainian oligar…
Google Cloud creates machine-learning group, describes technology and new GCP features
Kubernetes – From Evolution to an Established Ecosystem – Charting Stacks
report-peter-thiel-quietly-building-silicon-valley-bra-1789243996
Twitter
RT @aminatou: I grew up under 3 african dictators and certainly didn’t move to america for this deja vu
Internet2 Welcomes Google Cloud to its Community | Internet2 News
nternet2, announced today that Google has joined its community, a not-for-profit, member driven advanced technology and networking consortium dedicated to enabling innovation and scientific discoveries for the next generation of research and education. Google plans to work with Internet2 and its member institutions to explore higher education technology opportunities with Google Cloud Platform, which enables developers to build, test, and deploy applications on Google’s highly-scalable and reliable infrastructure.
Research Blog: How Robots Can Acquire New Skills from Their Shared Experience
The ability to learn from experience will likely be a key in enabling robots to help with complex real-world tasks, from assisting the elderly with chores and daily activities, to helping us in offices and hospitals, to performing jobs that are too dangerous or unpleasant for people. However, if each robot must learn its full repertoire of skills for these tasks only from its own experience, it could take far too long to acquire a rich enough range of behaviors to be useful. Could we bridge this gap by making it possible for robots to collectively learn from each other’s experiences?

While machine learning algorithms have made great strides in natural language understanding and speech recognition, the kind of symbolic high-level reasoning that allows people to communicate complex concepts in words remains out of reach for machines. However, robots can instantaneously transmit their experience to other robots over the network – sometimes known as "cloud robotics" – and it is this ability that can let them learn from each other.
Google’s AI can now learn from its own memory independently – ScienceAlert
The DeepMind artificial intelligence (AI) being developed by Google’s parent company, Alphabet, can now intelligently build on what’s already inside its memory, the system’s programmers have announced.

Their new hybrid system – called a Differential Neural Computer (DNC) – pairs a neural network with the vast data storage of conventional computers, and the AI is smart enough to navigate and learn from this external data bank.
Google acquires natural language understanding startup Api.ai | VentureBeat | Bots | by Jordan Novet
MXNet – Deep Learning Framework of Choice at AWS – All Things Distributed
Open Letter to Stephen Bannon from the Seven Sisters Presidents | Bryn Mawr College
We know what’s going on and we know what to do | Benlog
Dakota Access pipeline: 300 protesters injured after police use water cannons | US news | The Guardian
RT @juliacarriew: 26 hospitalized at #StandingRock after use of water cannon, sheriff says it’s "basically just a fire hose" #NoDAPL
Twitter
RT @marginoferror: Remember and even quote this the next time someone says it’s only humor, satire or sarcasm
Twitter
RT @doubleocherry: LOL @DLin71 @davidfrum