Multiply descent cost competitive learning as an aid for multimedia image processing
暂无分享,去创建一个
An integration of neural and ordinary computations toward multimedia processing is presented. The handled media is a combination of still images and animations. The neurocomputation here is the multiply descent cost competitive learning. This algorithm generates two types of feature maps. One of them: an optimized grouping pattern of pixels by self-organization, is used. A data-compressed still image can be recovered from this feature map by virtue of the multiply descent cost competitive learning. Next, this map is contorted according to a user's request. At the final step, a movie is virtually generated from the compressed still image via a set of animation tools. Thus, neurocomputation can be a useful item in the toolbox for creating the virtual reality besides the real-world computing.
[1] Yasuo Matsuyama. Multiple descent cost competitive learning: batch and successive self-organization with excitatory and inhibitory connections , 1990, 1990 IJCNN International Joint Conference on Neural Networks.