anomaly   456

« earlier    

Massive Scale Anomaly Detection Framework
Guy Gerson introduces an anomaly detection framework PayPal uses, focusing on flexibility to support different types of statistical and ML models, and inspired by scikit-learn and Spark MLlib.
anomaly_detection  anomaly  outlier  ml  mlops 
3 days ago by izgurskii
Gravity ‘anomaly’ at Moon’s south pole could be buried metallic asteroid • Extreme Tech
Ryan Whitwam:
<p>The leading explanation for the gravitational anomaly, <a href="">according to the researchers</a>, is that the object responsible for the crater is still mostly intact beneath the surface. So, some 4 billion years ago, a mostly metallic asteroid hit the moon and remains embedded in the mantle to this day. Another potential explanation is that the region is naturally rich in oxides that formed as the moon cooled in the distant past. However, the overlap of the crater and increased gravity seems a bit too convenient.

If there is a large metallic object buried under the South Pole-Aitken basin, it could tell us something about the moon’s interior. After four billion years, the iron-nickel remains of the asteroid would have been dispersed throughout the mantle if the moon was geologically active for any significant period of time.</p>

Ooooh is it a radio-opaque obelisk with proportions of 1:4:9? Looking forward to the expedition visiting it.
moon  anomaly  asteroid 
6 days ago by charlesarthur
yzhao062/pyod: A Python Toolkit for Scalable Outlier Detection (Anomaly Detection)
PyOD is a comprehensive and scalable Python toolkit for detecting outlying objects in multivariate data. This exciting yet challenging field is commonly referred as Outlier Detection or Anomaly Detection. Since 2017, PyOD has been successfully used in various academic researches and commercial products. PyOD is featured for:

Unified APIs, detailed documentation, and interactive examples across various algorithms.
Advanced models, including Neural Networks/Deep Learning and Outlier Ensem...
anomaly  anomaly-detection  machinelearning  python  deeplearning  neuralnetwork  github 
january 2019 by newtonapple
MentatInnovations/ An open-source framework for real-time anomaly detection using Python, ElasticSearch and Kibana
An open-source framework for real-time anomaly detection using Python, ElasticSearch and Kibana - MentatInnovations/
anomaly-detection  anomaly  python  elasticsearch  kibana  stream  timeseries  github 
january 2019 by newtonapple
linkedin/luminol: Anomaly Detection and Correlation library
Luminol is a light weight python library for time series data analysis. The two major functionalities it supports are anomaly detection and correlation. It can be used to investigate possible causes of anomaly. You collect time series data and Luminol can:

Given a time series, detect if the data contains any anomaly and gives you back a time window where the anomaly happened in, a time stamp where the anomaly reaches its severity, and a score indicating how severe is the anomaly compare to ...
anomaly  anomaly-detection  linkedin  python  timeseries  library 
january 2019 by newtonapple
Detecting Anomalies in Time Series Data: Deciphering the Noise and Zoning in on the Signals - insideBIGDATA
While each of the above techniques obviously has advantages as well as disadvantages, it’s only unsupervised anomaly detection that is feasible in the case of raw, unlabelled time series data – which is what you get from just about any online asset in a modern-day digitised company. Anomaly detection in time series data has a variety of applications across industries – from identifying abnormalities in ECG data to finding glitches in aircraft sensor data.
deeplearning  machinelearning  ml  anomalydetection  anomaly  unsupervised  timeseries 
january 2019 by dlkinney

« earlier    

related tags

$10  10  2fa  ai  alert  alerting  algorithm  algorithms  alien  aliens  analysis  analytics  ang  anomaly-detection  anomaly_detection  anomalydetection  antarctica  arizona  asteroid  atlantis  authentication  autoencoder  automated  aws  badluck  baidu  benchmark  bigdata  bizarre  break  challenge  change  cinc  climatechange  clustering  cnn  code  computer  conservatives  consistency  cruz  cs  cybersecurity  data  database  datascience  datascientist  dataset  datawrangling  death  decision  deeplearning  density  detect  detection  devices  devops  dfir  diff  diffraction  docker  dynamics  earth  earthquakes  economics  elasticsearch  electricity  electronics  ever  failure  field  forecasting  forest  fourier  fraud  free-speech  gcp  german  gfs  ghosts  github  globalwarming  golang  gravity  gyro  hardware  heart  hermitage  hesse  history  ids  ifttt  images  inference  influxdb  interference  intrusiondetection  isolation  jupyter  kaggle  kapacitor  karma  keras  keystroke  kibana  kleppmann  laser  latency  learning  library  light  lights  linkedin  log  login  london  lstm  machine-learning  machine  machinelearning  magnetometer  mapping  matlab  medical  meteo  metrics  ml  mlops  modsecurity  monitoring  moon  morgoth  most  mysterious  mystery  nature  navigation  network  neural  neuralnetwork  nginx  nids  online  opensource  outlier  outliers  packages  paper  paranormal  pattern  pcap  penalty  penalty:  people  photos  physics  physionet  pictures  point  prelert  puberty  python  qc  quantum  r  rate  recurrent  research  river  rnn  sampling  sans  santa  science  scraps  sdn  sec...  security  sensor  sensors  series  server  sex  simstadt  slider  software  spark  spot  state  statistics  stats  statsd  stream  sts  subsequence  survey  system  taken  technology  ten  tensorflow  threathunting  time-series  time  timeseries  top  traffic  tree  twins  ufo  unsupervised  video  vitals  viz  volatility  water  weather  wikipedia  wordpress 

Copy this bookmark: