Week 4 Comprehensive

Week 4 Comprehensive >> Introduction to Machine Learning

A vector of numbers associated with a word.

Assigning a corresponding number to each word.

A vector consisting of all words in a vocabulary.

The latitude and longitude of the place a word originated.

Embedding

Stack

Array

Norm

Space

Array

Embedding

Codebook

Translating human-readable code to machine-readable instructions.

Translating natural text characters to unicode representations.

Taking natural text and making inferences and predictions.

Making natural text conform to formal language standards.

Determine the vocabulary in the codebook.

Given a word, predict which words are in its vicinity.

Find the hidden or latent features in a text.

Labelling a text corpus, so a human doesn’t have to do it.

Softmax function

Exponential log likelihood

Squash function

Hyperbolic tangent function

Word n is used to predict the words in the neighborhood of word n.

Word n is learned from a large corpus of words, which a human has labeled.

The code for word n is fed through a CNN and categorized with a softmax.

Vectors for the neighborhood of words are averaged and used to predict word n.

The code for word n is fed through a CNN and categorized with a softmax.

Word n is used to predict the words in the neighborhood of word n.

Word n is learned from a large corpus of words, which a human has labeled.

Synthesize a sequence of words.

Classify an unlabeled image.

Learn a series of images that form a video.

Predict words more efficiently than Skip-Gram.

CNN

CBOW

Multilayer perceptron

Long short-term memory

Week 4 Comprehensive >> Introduction to Machine Learning