kaggle   1144

« earlier    

Kaggle Fundamentals: The Titanic Competition
Kaggle Fundamentals: The Titanic Competition - Added November 14, 2017 at 11:44AM
data-science  kaggle  read2of 
12 days ago by xenocid
kaggleメルカリコンペの表彰式イベントに参加してきました - 周回遅れでIT業界デビューしたエンジニアのブログ
“kaggleメルカリコンペの表彰式イベントに参加してきました - 周回遅れでIT業界デビューしたエンジニアのブログ”
kaggle  data_science  from twitter_favs
13 days ago by ocelot
GitHub - MLWave/Kaggle-Ensemble-Guide: Code for the Kaggle Ensembling Guide Article on MLWave
Code for the Kaggle Ensembling Guide Article on MLWave
A combination of Model Ensembling methods that is extremely useful for increasing accuracy of Kaggle's submission. For more information: http://mlwave.com/kaggle-ensembling-guide/
ensembling  kaggle  ml 
15 days ago by hellsten
Kaggle Ensembling Guide | MLWave
We will now show how these pseudo-classifiers are able to obtain 78% accuracy through a voting ensemble.

A pinch of maths
For a majority vote with 3 members we can expect 4 outcomes:

All three are correct
0.7 * 0.7 * 0.7
= 0.3429

Two are correct
0.7 * 0.7 * 0.3
+ 0.7 * 0.3 * 0.7
+ 0.3 * 0.7 * 0.7
= 0.4409

Two are wrong
0.3 * 0.3 * 0.7
+ 0.3 * 0.7 * 0.3
+ 0.7 * 0.3 * 0.3
= 0.189

All three are wrong
0.3 * 0.3 * 0.3
= 0.027
We see that most of the times (~44%) the majority vote corrects an error. This majority vote ensemble will be correct an average of ~78% (0.3429 + 0.4409 = 0.7838).
kaggle  ensembling  correlation  ml  ai 
15 days ago by hellsten
Datasets | Kaggle
The best place to discover and seamlessly analyze open data
datasets  kaggle  opendata  data  open 
8 weeks ago by wjy

« earlier    

related tags

advice  ai  amazon  analysis  anomaly  api  apis  autoencoder  beer  camera  career  code  comments  competition  convolutional-neural-networks  convolutions  cookies  cool  correlation  course  courses  credit-card  crop  curl  dae  data-analysis  data-science  data-sets  data  data_science  database  datascience  dataset  datasets  deep-learning  deep_learning  deeplearning  denoising-autoencoder  denoising  detection  differential-learning-rates  dog-breeds  eda  education  ensemble  ensembling  example  examples  exploratory-data-analysis  f2  fast.ai  fastai  fbeta  football  fraud-detection  fraud  gcp  github  google  gradient-boosting  graphs  guide  haze-removal  haze  hn  horse-racing  houseprices  jupyter  keras  language  learning-rate  learning  library  lightgbm  logging  loss  lstm  machine-learning  machine_learning  machinelearning  ml  model  models  netscape  network  neural-networks  nlp  normalization  notebook  number-one  omni-mate  open  opendata  outlier-detection  paper  papers  planet  plot  plots  plotting  pretrained  process  programming  python  pytorch  r  rankgauss  read2of  reference  regularisation  reinforcement-learning  reinforcement  relational  reproducibility  resnet  resources  rstats  sae  science  score  sdae  seaborn  sha256  sklearn  soccer  statistics  structured-data  talks  tensorflow  time-series-data  tips  titanic  toxic-comments  transfer-learning  translation  tricks  tutorial  tutorials  validation  visualisation  visualization  weather  wget  winner  word-cloud  xgboost  ycombinator  youtube  zoom 

Copy this bookmark: