Computer Vision

Why Machine Learning and computer vision:

           Much of the world's data is in the form of visual media. In order to utilize meaningful information from multimedia and deliver innovative products, such as Google Photos, Google builds machine-learning systems that are designed to enable computer perception of visual input, in addition to pursuing image and video analysis techniques focused on image/scene reconstruction and understanding.

 Conference: 2015 Conference on Computer Vision and Pattern Recognition (CVPR 2015)

 

Large Scale Visual Recognition Challenge Tutorial

Linear Combination of Vectors

Let us consider a basis vector, x=[1 2 3]

Now consider vectors ,y = [2 4 6] and z=[3 6 9]. What is your observation?

yes, the vector y is a scalar multiple of x. That is y=2x.

The vector z is a linear combination of y and x. That is z= y + 1.x. or z = 2.x +1.x. All possible linear combinations are called vector space.  So the vector z and y is linearly dependent vectors.

Inner Product:

Inner Product of x and y is: 1.2 +2.4 +3.6 =28

Machine Learning Tutorials

Microsoft Research:

Introduction To Bayesian Inference
Christopher Bishop


Standford:

2 videos
Generative Models for Visual Objects and Object Recognition via Bayesian Inference
Fei-Fei Li