The principle of choosing the initial values of weights for the layers that make up the model is very important. Setting all the weights to 0 is a severe obstacle to learning because none of the weights can be active initially. Assigning weights to the random values from the interval, [0, 1], is also usually not the best option. Actually, model performance and learning process convergence can strongly rely on correct weights initialization; however, the initial task and model complexity can also play an important role. Even if the task's solution does not assume a strong dependency on the values of the initial weights, a well-chosen method of initializing weights can significantly affect the model's ability to learn. This is because it presets the model parameters while taking the loss function into account. Let's look at two popular methods that are used to initialize weights.