Unit vectors are often used to standardize vectors, which is more convenient to compare vectors of different sizes. In addition, in physics, we can express the unit vector as the direction of physical quantity. For example, the direction of force can be expressed by a unit vector. In machine learning, we can also use unit vectors to describe data sets.
In two-dimensional space, the common unit vectors are e 1 = and e2 =, e2 = and e3 = [0 0,0, 1], which represent the X-axis, Y-axis and Z-axis directions respectively. In addition, the vector e can also represent any direction. For example, in machine learning, we can use orthogonal vector groups to represent unit vectors in any direction.