PCA search for the sub vector space (with reduced dimensio) for projection which allow the more accurate projection of the data.
Let
Let
Samples
Points of
Variances:
Eigen vector base:
Projection on the two first components (or the two last)
3D vs projection on the two first components (canonical representations) and the last.
Video images converted to color histrograms and visualized with the 2 first components of the PCA.
Algorithm minimizes:
Initilize
(average location of the group)
Partitionnement spectral:
Create a good features for a downstream task.
Create a pretext task to train the network on.
The labels for task a generated automatically.
This the real final objective. It could be classification, regression...
It is trained in a supervised manner.
To predict the transformation of an image, you must \textit{understand} what is in the image.
Random rotation of the image.
Four classes:
Simple classification problem.
Random rotation of the image.
Four classes:
Simple classification problem.
Pre-training: all data (no label)
Target: part of the data with labels
Random rotation of the image.
Four classes:
Simple classification problem.
Pre-training: all data (no label)
Target: part of the data with labels
Create a pair of patch, find their relative position.
To solve problem, you need to understand the object.
Create a pair of patch, find their relative position.
To solve problem, you need to understand the object.
Classification with 8 classes
Create a pair of patch, find their relative position.
To solve problem, you need to understand the object.
Classification with 8 classes
Predict a transformation of an image.
but may not require a complete knowledge of the object.
What properties the pre-trained network should have ?
Let
The loss function is:
A cross entropy applied label corresponding to the pair generated from
Unsupervised learning is one of the big thing in machine learning now.
• Can we extract better/general features?
• Can we reduce the training time?
• Do we really exploit all the information in the data?
Neural Network notes