Professional Documents
Culture Documents
Agenda
Linear Classification
Overview
Linear classifier
References
Linear Classification
Overview
Linear classifier
References
Contact Information
Linear Classification
2 Overview Linear
classifier
References
Linear Classification
3 Overview Linear
classifier
References
Linear Classification
4 Overview Linear
classifier
References
Linear Classification
5 Overview Linear
classifier
References
Linear Classification
Overview
References
linear mapping:
f (xi , W, b) = Wxi + b
) Image xi has all of its pixels flattened out to a single
column vector of shape [Dx1].
) The matrix W (of size [KxD]), and the vector b (of size
[Kx 1]) are the parameters of thefunction.
) The parameters in W are often called the weights, and b
is called the bias vector because it influences the output
scores, but without interacting with the actual data xi .
Linear Classification
Overview
7 Linear classifier
References
for 10 classes
Linear Classification
Overview
Linear classifier
References
8
Linear Classification
Overview
9 Linear classifier
References
Linear Classification
Overview
9 Linear classifier
References
Linear Classification
Overview
9 Linear classifier
References
Linear Classification
view
r classifier
Over
10 Linea
References
Linear Classification
view
r classifier
Over
10 Linea
References
Linear Classification
Overview
11 Linear classifier
References
Linear Classification
Overview
12 Linear classifier
References
Linear Classification
Overview
) Another interpretation for the weights W is that each row 13 Linear classifier
Linear Classification
Overview
14 Linear classifier
) Another interpretation for the weights W is that each row
References
of W corresponds to a template for one of the classes.
) The score of each class for an image is then obtained by
comparing each template with the image using a dot
product one by one to find the one that “fits” best.
) The linear classifier is doing template matching, where the
templates are learned.
Linear Classification
Overview
References
but once the learning is complete, we can discard the
entire training set and only keep the learned parameters.
Linear Classification
Overview
Linear Classification
Overview
References
but once the learning is complete, we can discard the
entire training set and only keep the learned parameters.
) That is because a new test image can be simply forwarded
through the function and classified based on the
computed scores.
) + To classifying the test image involves a single matrix
multiplication and addition, which is significantly faster
than comparing a test image to all training images.
Ghada Ahmed
Linear Classification
Overview
References
but once the learning is complete, we can discard the
entire training set and only keep the learned parameters.
) That is because a new test image can be simply forwarded
through the function and classified based on the
computed scores.
) + To classifying the test image involves a single matrix
multiplication and addition, which is significantly faster
than comparing a test image to all training images.
) Convolutional Neural Networks will map image pixels to
scores exactly as shown above, but the mapping (f ) will be
more complex and will contain more parameters.
Ghada Ahmed
Linear Classification
Overview
16 Linear classifier
References
Ghada Ahmed
Linear Classification
Overview
17 Linear classifier
References
Ghada Ahmed
Linear Classification
Overview
Linear classifier
) Online: 18 References
http://www.computervisionblog.com/2015/03/deep-
learning-vs-machine-learning-vs.html
) Online: http://nkonst.com/machine-learning-explained-
simple-words/
linear-classifier Demo
http://vision.stanford.edu/teaching/cs231n-demos/linear-
classify/
) Book: François Chollet, Deep learning with Python
Cross-Validation
https://scikit-
learn.org/stable/modules/generated/sklearn.model_selectio
n.KFold.html#sklearn.model_selection.KFold
Dept. of Computer Science
19 Helwan University