CNN forText Classification describes how convolutional neural networks (CNNs) can be used for text classification. CNNs apply convolution operations to input data to identify patterns. For natural language processing, CNNs convolve filters over word vectors or embeddings to analyze n-grams. The model is adapted from a 2014 paper and applies convolution and max pooling layers to classify sentences.
2. What are
Convolutions?
A convolution is an
integral that expresses the
amount of overlap of one
function as it is shifted
over another function
Can be thought as
"blending" functions
Pictures found on Christopher Olah's blog, originally
from Wikipedia 2
Definition from Wolfram Alpha's page on
convolution 1