O GoConqr está de visual novo! Conte para nós o que você achou.

Flashcards

Machine learning

Usuário eliminado O usuário eliminou as informações de disciplina Inglês 11 flashcards

Flashcards do conjunto (11)

  1. 1What is machine learning?Methodology for onstructing models to predict properties of data
  2. 2What is the difference between supervised and unsupervised learningThe knowledge of the output values(known/unknown)
  3. 3What is special about reinforcement learning?The model learns behavior in an environment
  4. 4How is the output of a node determined?By the activation funtion
  5. 5How is the error handled in a neural network?Backpropagation
  6. 6How can input be encoded?Dummy coding or vector representation(word embedding)
  7. 7Why is input encoding needed?to be able to represent a large number of category values in a relatively compact input space
  8. 8What does the distributional hypothesis say?It states that words that often
    occur in a similar context are semantically similar
  9. 9A standard neural network has a single set of weights, a recurrent neural network (RNN) has two sets of weights, and a Long Short Term Memory (LSTM) network has three sets of weights. What is the purpose of the extra sets of weights for the RNN and LSTM models?for the RNN, the extra weights are used to incorporate the output of the previous element in a sequence into the output of the current element. For the LSTM, the third set of weights is used to maintain a cell state, which models long term dependencies beyond just the previous element.
  10. 10What is the purpose of a word embedding in text classification?word embeddings are used as a dimension reduction technique, to be able to represent a large number of category values in a relatively compact input space.
  11. 11Given the words 'pizza', 'pasta' and 'recursion', construct 5-dimensional word embeddings with two significant digits for each word such that the semantic similarity between the words is preserved.for example pizza = [0.46,0.88,0.21,0.23,0.52], pasta = [0.43,0.81,0.77,0.19,0.52], recursion = [0.12,0.03,0.54,0.98,0.80].

Informações

Descrição
O usuário eliminou as informações de disciplina FlashCards sobre Machine learning, criado por Usuário eliminado em 03-11-2018.
Criado por
Usuário eliminado · nov 2018
Atualizado
3 nov 2018
Visualizações
87
Histórico
  • Criado por August Edström · 2 nov 2018
  • Copiado por August Edström · 3 nov 2018
Avaliação

Fale Conosco

Sobre o que é sua mensagem?

O que você acha do novo visual?

Você gostou?