Weight initialization method and apparatus for stable learning of deep learning model using activation function

An artificial neural network learning apparatus for deep learning, comprising:

• an input unit configured to acquire an input data or a training data;
• a memory configured to store the input data, the training data, and a deep learning artificial neural network model;
• and
• a processor configured to perform computation based on the artificial neural network model,
• wherein the processor sets an initial weight affecting an activation function between a first node and a second node subsequent to the first node of the artificial neural network model, the first node being included in a first layer and the second node being included in a second layer,
• wherein the processor sets the initial weight depending on the number of nodes belonging to the first layer and the number of nodes belonging to the second layer of the artificial neural network model, and
• wherein the processor determines the initial weight by compensation by multiplying a standard deviation (σ) by a square root of a reciprocal of a probability of a normal probability distribution for a remaining section except for a section in which an output value of the activation function converges to a specific value.