Markany Inc.

Seung Yeob Chae

So Won Kim

Min Soo Park

Tai Yoon Lee

Hyungyu Kim

Provided is an artificial neural network learning apparatus for deep learning. The apparatus includes 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, in which the processor sets the initial weight depending on the number of nodes belonging to a first layer and the number of nodes belonging to a second layer of the artificial neural network model, and determines the initial weight by compensation by multiplying a standard deviation (&#x3c3;) 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.

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

One aspect of the present invention discloses an apparatus for detecting additional data for preventing forgery of video data and displaying the video content. The apparatus includes a content input unit configured to receive the video content (the video content including the additional data), a display unit configured to display the video content, an additional data detector configured to detect the additional data from the video content (the additional data including a watermark), and a display controller configured to control a display screen of the video content according to an additional data detection result.

Apparatus, method and system for detecting additional data for preventing forgery of video content, rendering apparatus interoperating with display apparatus, and rendering method thereof

Growing community of inventors

Seoul, South Korea

Seung Yeob Chae