Keep yourself updated with Halit Eriş.
ANNOUNCEMENTS & BLOG
Welcome to Digital Castle. You can find lab groups, upcoming announcements and experimental procedure details for Digital Design, Numerical Methods, Programmable Logic Circuits and Embedded Systems lecture. All the information about upcoming classes will be introduced here.
A quick survey !
Any trend topics?
2020 - 2021 can be assumed to be a breath-taking year for deep learning supported image generation. Deep-fake and Deep-dream applications spread-wide all over the internet and also it is easily implemented on any sample image or video instantly using mobile apps. But, what are Deep-fake and Deep-dream?
"How fascinating it is to imagine a computer that, dreams?"
Deep-Dream is a computer vision program created by Google engineer Alexander Mordvintsev that uses a convolutional neural network to find and enhance patterns in images via algorithming a dream-like hallucinogenic appearance in the deliberately over-processed images. Here, see for yourself:
"Mona Lisa" with DeepDream effect using VGG16 network trained on ImageNet
"Nothing is real, everything is permitted."
Deep-Fake is artificial media in which a person in an existing image or video is replaced with someone else's likeness. While the act of faking content is not new,
Deep-Fakes leverage powerful techniques from machine learning to manipulate or generate visual and audio content with a high potential to deceive.
In a scene from Man of Steel, actress Amy Adams in the original (left) is modified to have the face of actor Nicolas Cage (right)