classification   10442

« earlier    

Keras vs PyTorch: how to distinguish Aliens vs Predators with transfer learning
This article was written by Piotr Migdał, Rafał Jakubanis and myself. In the previous post, they gave you an overview of the differences between Keras and PyTorch, aiming to help you pick the…
tutorials  images  classification  keras  torch 
14 days ago by arnicas
What Kagglers are using for Text Classification
With the problem of Image Classification is more or less solved by Deep learning, Text Classification is the next new developing theme in deep learning. For those who don't know, Text classification is a common task in natural language processing, which transforms a sequence of text of indefinite length ...
DeepLearning  bidirectional  attention  classification  lstm  text  nlp  ml 
20 days ago by grinful
"This site contains several years of research in the classification of occlupanids. These small objects are everywhere, dotting supermarket aisles and sidewalks with an impressive array of form and color. The Holotypic Occlupanid Research Group has taken on the mantle of classifying this most common, yet most puzzling, member of phylum Plasticae."
taxonomy  academia  classification  biology  science  parody  art 
24 days ago by aparrish
ARTigo – Social Image Tagging [Dataset and Images]
ARTigo is a platform that uses crowdsourcing to gather annotations (tags) on works of art (see The dataset is compromised of 54.497 objects, which are associated with 18.492 artists (11.519 of which are either anonymous or unknown), 295. via Pocket
art  classification  crowdsourcing  datasets  germany  images  munich 
25 days ago by kintopp
[1808.08414] Unsupervised Hypergraph Feature Selection via a Novel Point-Weighting Framework and Low-Rank Representation
Feature selection methods are widely used in order to solve the 'curse of dimensionality' problem. Many proposed feature selection frameworks, treat all data points equally; neglecting their different representation power and importance. In this paper, we propose an unsupervised hypergraph feature selection method via a novel point-weighting framework and low-rank representation that captures the importance of different data points. We introduce a novel soft hypergraph with low complexity to model data. Then, we formulate the feature selection as an optimization problem to preserve local relationships and also global structure of data. Our approach for global structure preservation helps the framework overcome the problem of unavailability of data labels in unsupervised learning. The proposed feature selection method treats with different data points based on their importance in defining data structure and representation power. Moreover, since the robustness of feature selection methods against noise and outlier is of great importance, we adopt low-rank representation in our model. Also, we provide an efficient algorithm to solve the proposed optimization problem. The computational cost of the proposed algorithm is lower than many state-of-the-art methods which is of high importance in feature selection tasks. We conducted comprehensive experiments with various evaluation methods on different benchmark data sets. These experiments indicate significant improvement, compared with state-of-the-art feature selection methods.
classification  feature-selection  rather-interesting  hypergraphs  to-understand  machine-learning  to-do 
26 days ago by Vaguery
Document classification - Wikipedia
Document classification or document categorization is a problem in library science, information science and computer science. The task is to assign a document to one or more classes or categories. This may be done "manually" (or "intellectually") or algorithmically. The intellectual classification of documents has mostly been the province of library science, while the algorithmic classification of documents is mainly in information science and computer science. The problems are overlapping, however, and there is therefore interdisciplinary research on document classification.
The documents to be classified may be texts, images, music, etc. Each kind of document possesses its special classification problems. When not otherwise specified, text classification is implied.
classification  bookmarks  curation  taxonomy 
27 days ago by euler

« earlier    

related tags

2018  551  academia  africa  agriculture  ai  airfares  algorithm  algorithms  analysis  animals  annotation  api  app  archives  art  arthistory  artificial_intelligence  artificialintelligence  artist  asiamurphy  attention  automation  badmodels  bayestheorem  bias  bidirectional  billgates  biology  bison  bloodparks  bogdkhan  book  bookmarks  botany  botswana  britain  callnumbers  carllinneaus  cataloging  cataloguing  categorization  causality  china  citibike  classifier  climatechange  clustering  cnn  code  collaboration  colonialism  color  colour  computerscience  computervision  congo  conservation  content-abuse  content  controlledvocab  cooking  cpc  critlib  crowdsourcing  curation  data  databases  datascience  dataset  datasets  dataviz  dates  decision  decisiontrees  deep_fakes  deeplearning  deforestation  delineation  design  design_anthro  dev  development  device  digital_labor  document  documentary  drc  earth  ecology  economics  ecosystems  ecotourism  elephants  embeddings  environement  epistemology  equity  escooter  ethics  eugenics  europe  evaluation-measures  evaluation  exploitation  extinction  fairness  fares  farming  favorites  feature-selection  finland  floss  fonts  food  forests  fungi  game  gender  generative  geography  geometry  georgescuvier  germany  glboalnorth  globalsouth  google  guide  handwriting  hinkelmann  history  hn  humanities  humor  hybridity  hypergraphs  ideas  identification  image  imageprocessing  imagerecognition  images  imperialism  inclassactivities  indexing  india  indigeneity  indigenous-peoples  indigenous  indigenouspeople  inequality  infographics  ireland  italy  ivory  jobs  kaggle  keras  knowledge_organization  label  labor  land  landmangement  language  learn  learning  legal  libraries  library2.0  lists  loc  local  lstm  lynnmeskell  machine-learning  machine.learning  machine  machine_learning  machinelearning  madagascar  maheshrangarajan  management  manual  manuscripts  maori  maps  matrices  mediashift  metrics  mining  mistakesweremade  ml  model  money  mongolia  morethanhuman  multi  multispecies  munich  namibia  naming  nationalparks  naturalresources  nature  ndl301  nepal  network  neural  neuralnets  neuralnetworks  news  newzealand  nezperce  ngos  nlp  nyc  oak  of  opensource  oppression  organization  parody  patent  patents  people  person  photography  photos  pht235  pipeline  places  poaching  porn  programming  property  prosopography  python  quantum-computing  race  racism  radlib  rather-interesting  recipes  recognition  recommendation  regression  representation  research  resources  rnn  salad  salads  sandwiches  science  scientificracism  search  searching  service  set  sexism  shape  shopping_carts  signs  socialeffects  socialjustice  somalia  soup  space  spam  species  standardization  standards  states  stats  stray_carts  subject_headings  sumatra  svm  taxonomy  tensorflow  terranullis  test  text-classification  text  text_analysis  theory  tigers  timber  to-do  to-understand  tool  tools  topic  torch  tourism  trainingsets  transportation  tree  truth  tufte  tutorial  tutorials  type  ual  ulm  united.airlines  united  universal_decimal  us  vehicle  video  virunga  vision  vocabularies  vox  waterbody  weird  welth  westernism  wildlife  word2vec  work  xwi7xwa_library  yellowstone  zimbabe 

Copy this bookmark: