dl   2657

« earlier    

[1511.06443] Neural Network Matrix Factorization
Seems relevant for heterogeneous data. Could be extended.
matrix-factorization  DL  heterodata 
8 days ago by gideonite
Deep learning is only as good as its data | VentureBeat
A key issue for machine learning algorithms is selection bias. In sound research, you can define the population, have access to all available population data, and sample a portion of that data. With deep learning, you start with sample data, deploy the model, and then expose it to the real world. But models that work well on training data often perform poorly on real data. Deep learning provides the ability to accurately determine the classification function from inputs to an output. However, there is no guarantee that the model will perform accurately on input data from the population if the training data is not representative.

This data failure is more common when training data isn’t developed by domain experts. While deep learning might eliminate the need to have domain experts in the feature extraction part of the classification process, it still requires expertise in the data extraction process. In fact, deep learning might be overkill when a domain expert can explicitly describe the linear or nonlinear function using logic and rules.
dl  ml  ai  statistics 
22 days ago by paulbradshaw
Twitter
Cognitive Science: What Is It and Why Is It Important?
by |

DeepLearning  DataScience  ML  DL  from twitter_favs
24 days ago by JINHONG

« earlier    

related tags

*****  advice  ai  analytics  and  artificialintelligence  backprop  bigdl  blog  book  books  brain  ca  caffe  clojure  cloud-detection  cnn  code  comics  course  crack  cs  css  data-science  datascience  debugging  deep-learning  deep  deeplearning  diabetes  diet-keto  disney  doc  download  downloading  dr_steven_gundry  ebooks  face  federated  fl  food-eggs  forums  framework  free  functional-foods  gan  generator  gpu  graph  grid  guru  heterodata  hn  hormones-isoflavones  imagenet  imageprocessing  intel  ios  irrigation  ivoox  keras  l  learn  lecture  lib  linalg  list  lstm  machine-learning  machinelearning  manga  math  matrix-factorization  matrix  mit  ml-interpretability  ml  more  movies  music  muy_muy_muy_bueno  neuralnetworks  neuroscience  news  nlp  nn  notebooks  now  numpy  nvidia  opendirectories  overview  p?  papers  pc  photography  photomanip  portable  posted  pretrained-models  probability  programming  py  python  r  readings  review  rnn  robot  rs  scans  script  shell  shmoo  software  softz  statistics  stats  sweeteners  system  tensor  tensorflow  throw  ti  tools  toss  toxins-heavy_metals  training  tricks  tut  videos  visualization  viz  warez  wdw  weightloss  wiki  windows  with  wiz  workshops  youtube  zoo  グラフ理論  チャーン  データ  データサイエンス  データ分析  ネットワーク分析  ファネル  機械学習  統計  論文  離脱 

Copy this bookmark:



description:


tags: