UNDERSTANDING
CONVOLUTIONAL NEURAL
NETWORKS FOR NLP EXAM
LATEST UPDATE (QUESTIONS
AND VERIFIED SOLUTIONS)
Convolu'onal Neural Network
In machine learning, a convolu'onal neural network (CNN, or convnet) is a
class of deep, feed-forward ar'ficial neural networks that has successfully been
applied to analyzing visual imagery.
Cnns use a varia'on of mul'layer perceptrons designed to require minimal
preprocessing. They are also known as shiE invariant or space invariant
ar'ficial neural networks (SIANN), based on their shared-weights architecture
and transla'on invariance characteris'cs.
Computer Vision
Computer vision is an interdisciplinary field that deals with how computers can
be made for gaining high-level understanding from digital images or videos.
From the perspec've of engineering, it seeks to automate tasks that the
human visual system can do.
Natural Language Processing
A field of computer science, ar'ficial intelligence concerned with the
interac'ons between computers and human (natural) languages, and, in
par'cular, concerned with programming computers to fruiLully process large
natural language data.
, Challenges in natural language processing frequently involve speech
recogni'on, natural language understanding, and natural language genera'on.
Convolu'on
The for me easiest way to understand a convolu'on is by thinking of it as a
sliding window func'on applied to a matrix.
The sliding window is called a kernel, filter, or feature detector. Say we use a
3×3 filter, mul'ply its values element-wise with the original matrix, then sum
them up.
To get the full convolu'on we do this for each element by sliding the filter over
the whole matrix.
This emulates the response of an individual neuron to visual s'muli.
Kernel
Sliding window used in a convolu'on.
Filter
Sliding window used in a convolu'on.
Feature Detector
Sliding window used in a convolu'on.
Hadamard Product
Mul'ply Values Element-Wise: A binary opera'on that takes two matrices of
the same dimensions, and produces another matrix where each element ij is
the product of elements ij of the original two matrices. It should not be
confused with the more common matrix product.
CONVOLUTIONAL NEURAL
NETWORKS FOR NLP EXAM
LATEST UPDATE (QUESTIONS
AND VERIFIED SOLUTIONS)
Convolu'onal Neural Network
In machine learning, a convolu'onal neural network (CNN, or convnet) is a
class of deep, feed-forward ar'ficial neural networks that has successfully been
applied to analyzing visual imagery.
Cnns use a varia'on of mul'layer perceptrons designed to require minimal
preprocessing. They are also known as shiE invariant or space invariant
ar'ficial neural networks (SIANN), based on their shared-weights architecture
and transla'on invariance characteris'cs.
Computer Vision
Computer vision is an interdisciplinary field that deals with how computers can
be made for gaining high-level understanding from digital images or videos.
From the perspec've of engineering, it seeks to automate tasks that the
human visual system can do.
Natural Language Processing
A field of computer science, ar'ficial intelligence concerned with the
interac'ons between computers and human (natural) languages, and, in
par'cular, concerned with programming computers to fruiLully process large
natural language data.
, Challenges in natural language processing frequently involve speech
recogni'on, natural language understanding, and natural language genera'on.
Convolu'on
The for me easiest way to understand a convolu'on is by thinking of it as a
sliding window func'on applied to a matrix.
The sliding window is called a kernel, filter, or feature detector. Say we use a
3×3 filter, mul'ply its values element-wise with the original matrix, then sum
them up.
To get the full convolu'on we do this for each element by sliding the filter over
the whole matrix.
This emulates the response of an individual neuron to visual s'muli.
Kernel
Sliding window used in a convolu'on.
Filter
Sliding window used in a convolu'on.
Feature Detector
Sliding window used in a convolu'on.
Hadamard Product
Mul'ply Values Element-Wise: A binary opera'on that takes two matrices of
the same dimensions, and produces another matrix where each element ij is
the product of elements ij of the original two matrices. It should not be
confused with the more common matrix product.
