EPISODE · Feb 2, 2018 · 8 MIN
DeepFakes Explained
from Siraj Raval
Theres a new trend on the interwebs called 'Deepfakes', a machine learning system that can be trained to paste one person's face onto another person's body, complete with facial expressions. The effect isn't yet more convincing than conventional computer graphics techniques, but it could democratize Hollywood-level special effects fakery - and, potentially, lead to a flood of convincing hoaxes. I'll explain how DeepFakes works both programmatically and thoeretically in this video. It's essentially 2 autoencoders trained on 2 image datasets and then we reconstruct image A using image B's decoder. Code for this video (with coding challenge): https://github.com/llSourcell/deepfakes Challenge winner: https://github.com/ivanklimuk/DNA_to_RNA Runner-up (Paramdeep): https://github.com/ParmuSingh/autoencoder-mnist Please Subscribe! And like. And comment. That's what keeps me going. Want more education? Connect with me here: Twitter: https://twitter.com/sirajraval Facebook: https://www.facebook.com/sirajology instagram: https://www.instagram.com/sirajraval More learning resources: https://www.youtube.com/watch?v=Uivy6vnP2B0 https://www.youtube.com/watch?v=yhvK_VFVfhw https://www.youtube.com/watch?v=8Pm4EDofw4c https://www.youtube.com/watch?v=nCSOLVw6gi8 https://www.youtube.com/watch?v=RL-wyUEqXYM Join us in the Wizards Slack channel: http://wizards.herokuapp.com/ And please support me on Patreon: https://www.patreon.com/user?u=3191693
What this episode covers
Theres a new trend on the interwebs called 'Deepfakes', a machine learning system that can be trained to paste one person's face onto another person's body, complete with facial expressions. The effect isn't yet more convincing than conventional computer graphics techniques, but it could democratize Hollywood-level special effects fakery - and, potentially, lead to a flood of convincing hoaxes. I'll explain how DeepFakes works both programmatically and thoeretically in this video. It's essentially 2 autoencoders trained on 2 image datasets and then we reconstruct image A using image B's decoder. Code for this video (with coding challenge): https://github.com/llSourcell/deepfakes Challenge winner: https://github.com/ivanklimuk/DNA_to_RNA Runner-up (Paramdeep): https://github.com/ParmuSingh/autoencoder-mnist Please Subscribe! And like. And comment. That's what keeps me going. Want more education? Connect with me here: Twitter: https://twitter.com/sirajraval Facebook: https://www.facebook.com/sirajology instagram: https://www.instagram.com/sirajraval More learning resources: https://www.youtube.com/watch?v=Uivy6vnP2B0 https://www.youtube.com/watch?v=yhvK_VFVfhw https://www.youtube.com/watch?v=8Pm4EDofw4c https://www.youtube.com/watch?v=nCSOLVw6gi8 https://www.youtube.com/watch?v=RL-wyUEqXYM Join us in the Wizards Slack channel: http://wizards.herokuapp.com/ And please support me on Patreon: https://www.patreon.com/user?u=3191693
NOW PLAYING
DeepFakes Explained
No transcript for this episode yet