¡Hola, Mundo!

Vector inner dot product Given two vectors of the same dimension, each component of the vector is multiplied and then added to create a scalar value.  u → = ( a , b ) v → = ( c , d ) u → ⋅ v → = a ⋅ c + b ⋅ d" data-ke-type="html">HTML 삽입미리보..

Markov Decision Process - Decision : Sequence of Actions.- S1 : It absorbed S0, a0 to indicate a1.- a1 : It is given by S1. If only S1 is given, a1 is determined regadless of S0, a0. https://youtu.be/DbbcaspZATg?si=KgUq5CdJKzHj9QOJ : Probability of what action to do in time t, state t. That is, distribution of what action to do in a particular state.The policy determines the action." data-ke-typ..

Q-Learning It is the process of finding famous restaurants by moving up, down, left, and right from the starting point on this map. In other words, it is a process that induces the fastest way to find this restaurant. The process of learning Q-Value. Episode A sequence of interactions between an agent and its environment, starting from an initial state and ending at a terminal state. In other wo..

Image Homographies Adjust the angle.Here are several consecutive images taken. Attach these images in order.Images are put together alternately. This is because the angle of the picture is different. Use Homography to adjust the angle. It requires 3 conditions. 1. The subject should be plane. 2. If it's not a plane, at least it should be close to a plane.Because even if it's not actually a plane..

The tree(3D) ←→ Camera(2D) The tree : The point we're seeing with our eyes, 3D point which has world coordinateCamera : When we take the tree, it transforms to 2DWhen we take the picture of the tree, the camera influenced by the Camera intrinsic parameters-lens, the distance between the lens and the image sensor, the angle between the lens and the image sensor, etc. Therefore, when finding the p..