amy + google   536

The Future of Work
Google ‘worker revolt’
google  activism 
2 days ago by amy
Alphabet’s Controversial Chief Legal Officer, David Drummond, Leaves Company
Alphabet’s controversial chief legal officer, David Drummond, is leaving the company, effective January 31. 

Drummond, an employee of nearly 20 years, was being scrutinized as part of a board investigation into the company’s handling of sexual misconduct for claims that he had inappropriate relationships with other workers. The probe also included the handling of allegations against Android creator Andy Rubin, who reportedly received a $90 million exit package after the company found sexual assault claims against him credible (Rubin denied wrongdoing at the time of the report). 

A company spokesperson said that Drummond will not be receiving an exit package. 
google  gender 
6 weeks ago by amy
Self-training with Noisy Student improves ImageNet classification
We present a simple self-training method that achieves
87.4% top-1 accuracy on ImageNet, which is 1.0% better
than the state-of-the-art model that requires 3.5B weakly labeled Instagram images. On robustness test sets, it improves
ImageNet-A top-1 accuracy from 16.6% to 74.2%, reduces
ImageNet-C mean corruption error from 45.7 to 31.2, and
reduces ImageNet-P mean flip rate from 27.8 to 16.1.
To achieve this result, we first train an EfficientNet model
on labeled ImageNet images and use it as a teacher to generate pseudo labels on 300M unlabeled images. We then
train a larger EfficientNet as a student model on the combination of labeled and pseudo labeled images. We iterate
this process by putting back the student as the teacher. During the generation of the pseudo labels, the teacher is not
noised so that the pseudo labels are as good as possible.
But during the learning of the student, we inject noise such
as data augmentation, dropout, stochastic depth to the student so that the noised student is forced to learn harder from
the pseudo labels
machine_learning  TensorFlow  google 
november 2019 by amy
GitHub - google/jax: Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
JAX is Autograd and XLA, brought together for high-performance machine learning research.

With its updated version of Autograd, JAX can automatically differentiate native Python and NumPy functions. It can differentiate through loops, branches, recursion, and closures, and it can take derivatives of derivatives of derivatives. It supports reverse-mode differentiation (a.k.a. backpropagation) via grad as well as forward-mode differentiation, and the two can be composed arbitrarily to any order.

What’s new is that JAX uses XLA to compile and run your NumPy programs on GPUs and TPUs. Compilation happens under the hood by default, with library calls getting just-in-time compiled and executed. But JAX also lets you just-in-time compile your own Python functions into XLA-optimized kernels using a one-function API, jit. Compilation and automatic differentiation can be composed arbitrarily, so you can express sophisticated algorithms and get maximal performance without leaving Python.

Dig a little deeper, and you'll see that JAX is really an extensible system for composable function transformations. Both grad and jit are instances of such transformations. Another is vmap for automatic vectorization, with more to come.
machine_learning  google  python 
october 2019 by amy
GoogleContainerTools/skaffold: Easy and Repeatable Kubernetes Development
Skaffold is a command line tool that facilitates continuous development for Kubernetes applications. You can iterate on your application source code locally then deploy to local or remote Kubernetes clusters. Skaffold handles the workflow for building, pushing and deploying your application. It also provides building blocks and describe customizations for a CI/CD pipeline.
kubernetes  development  google 
september 2019 by amy
GitHub - google/differential-privacy

This project contains a C++ library of ε-differentially private algorithms, which can be used to produce aggregate statistics over numeric data sets containing private or sensitive information. In addition, we provide a stochastic tester to check the correctness of the algorithms.
privacy  google 
september 2019 by amy
DeepMind and Waymo: how evolutionary selection can train more capable self-driving cars | DeepMind
If a member of the population is underperforming, it’s replaced with the “progeny” of a better performing member. The progeny is a copy of the better performing member, with slightly mutated hyperparameters. PBT doesn’t require us to restart training from scratch, because each progeny inherits the full state of its parent network, and hyperparameters are updated actively throughout training, not at the end of training.
google  machine_learning 
august 2019 by amy
Affordable noninvasive continuous blood glucose concentration monitoring via interferometry and thermal technology

Affordable noninvasive continuous blood glucose concentration monitoring via interferometry and thermal technology
google  science  health 
july 2019 by amy
GoogleCloudPlatform/berglas: A tool for managing secrets on Google Cloud
Berglas is a command line tool and library for storing and and retrieving secrets on Google Cloud. Secrets are encrypted with Cloud KMS and stored in Cloud Storage.

As a CLI, berglas automates the process of encrypting, decrypting, and storing data on Google Cloud.

As a library, berglas automates the inclusion of secrets into various Google Cloud runtimes

Berglas is not an officially supported Google product.
encryption  gcp  google 
april 2019 by amy
Chrome Extension for scheduling Jupyter Notebooks : datascience
We're currently developing a Chrome Extension for Jupyter Notebooks that includes:

Scheduling (e.g. automatically run a notebook daily, hourly, or every 5 minutes)

Tight integrations with Google Sheets and Slack (e.g. automatically send DataFrames to Google Sheets to share with non-technical teammates)

Collaboration features (e.g. share code amongst your team)

We're looking for beta users to help test and shape the product. The first version is live on the Web Store, so please give it a shot and let me know if you run into any problems or have any suggestions to make it better!

A little more on scheduling:

Open the extension while on the Notebook you want scheduled

Select your interval (e.g. daily, hourly, etc.)

Save the schedule

This notebook will now run on a Google Cloud Compute Engine at your set interval. The engine image is one of Google's Deep Learning VM's, which comes with many popular Python packages, but if you need another package, please let me know! I'm keeping a running list of the most requested packages and will add them this week.
google  gcp  dlvm  jupyter  chrome 
april 2019 by amy
SeekWell - Chrome Web Store
Schedule a Notebook to refresh automatically with a couple clicks, right from Jupyter Notebooks. Update Pandas DataFrames weekly, daily, hourly or every 5 minutes, and share the data with your team via Slack or Sheets!

SeekWell works within the tools you're already using:

Jupyter Notebooks:

Simply open the extension while in a Notebook, choose how often you want the data to refresh, and click schedule. No more building complex scheduling scripts from scratch or manually running analysis and reports.
dlvm  google  gcp  jupyter 
april 2019 by amy
[1902.01046] Towards Federated Learning at Scale: System Design
Federated Learning is a distributed machine learning approach which enables model training on a large corpus of decentralized data. We have built a scalable production system for Federated Learning in the domain of mobile devices, based on TensorFlow. In this paper, we describe the resulting high-level design, sketch some of the challenges and their solutions, and touch upon the open problems and future directions.
google  TensorFlow  machine_learning 
march 2019 by amy
Been Kim Is Building a Translator for Artificial Intelligence | Quanta Magazine
Neural networks are famously incomprehensible — a computer can come up with a good answer, but not be able to explain what led to the conclusion. Been Kim is developing a “translator for humans” so that we can understand when artificial intelligence breaks down.
google  machine_learning 
january 2019 by amy
« earlier      
per page:    204080120160

related tags

#analytics  #Android  #Apple  #books  #cablegate  #charts  #china  #chine  #copyright  #EMI  #google  #gov20  #netneutrality  #oracle  #paywalls  #swpats  #times  #verizon  #w2s  #wave  #Zeitgeist  &  @andreaswpv  @emilychang  @jason_pontin  @jayrosen_nyu  @om  aarchitecture  academia  ack  activism  advertising  africa  AfriTechSummit  aggregator  AI  ajax  amazon  amusements  analysis  analytics  android  api  apis  AppEngine  Apple  archive  arghh  art  artificial_intelligence  attention  austin  australia  automl  aws  Beam  bias  bigdata  bigquery  big_data  bioinformatics  biology  blog  blogs  books  browsers  business  cablegate  cbp  censorship  charts  china  chine  chrome  civil_liberties  climate  cloud  cloud_computing  cmle  cocoa  collaboration  collaborative_filtering  comment  computers  computer_languages  computer_science  computing  conspiracy_theories  container  cool  copyright  cryptography  culture  data  database  databases  Dataflow  datamining  datasets  datastore  data_science  deeplearning  deep_learning  design  design_patterns  development  devops  discovery  discrimination  distributed  diversity  dlvm  dna  docker  documentation  drosophila  ec2  economics  education  email  EMI  encryption  engineering  essays  ethics  fairness  federated_learning  feedly  firefox  fonts  framework  frameworks  from  gae  GANs  gce  gcp  gcs  gender  genetics  genomics  geo  geocoding  geography  geolocation  geometry  ghana  gke  gmail  gokit  golang  google  GoogleNext19  gov20  government  gps  graphics  greasemonkey  grid  gwt  hardware  health  healthcare  history  hmm  hosting  huh  human_rights  identity  images  image_processing  india  innovation  internet  interview  interviews  ios5  iot  iphone  java  javascript  journalism  jruby  json  jupyter  k8s  kaggle  kindle  kml  kubeflow  kubernetes  labor  language  law  libraries  library  mac  machine_learning  mapping  mapreduce  maps  markup  mashups  md  media  medicine  metadata  microformats  mobile  moi  museums  mysql  netflix  netneutrality  network  networks  net_neutrality  neuroscience  news  nlp  nosql  nytimes  objective-c  ocr  opendata  opensource  open_source  optimization  oracle  oscon  oss  osx  paywalls  personalization  photography  photos  photoshop  php  politics  portals  presentations  privacy  productivity  programming  protocols  pubsub  python  pytorch  qr_codes  quantum_computing  rails  rdbms  reference  reinforcement-learning  religion  research  RL  robotics  ruby  s2  s3  scalability  science  search  seattle  security  semantic_web  seq2seq  serverless  sexism  Shared  sharing  social_media  society  software  software/social  spanner  spinnaker  standards  startups  statistics  storage  surveillance  swift  swpats  sydney  tagging  tbr  technology  TensorFlow  times  tips  tools  translation  travel  tutorial  tutorials  twitter  twitter_fav  typography  udacity  usa  usability  utilities  verizon  video  videos  visualization  visualizations  w2s  wave  Weather  web  web_design  web_dev  web_services  workshops  writing  xai  xml  Zeitgeist  Zend 

Copy this bookmark: