Generative Design with Generative Neural Networks
AI Creates 3D Models From Images
A new Two Minute Papers #186
AI Creates Facial Animation From Audio
A new Two Minute Papers #185
Sept 4, 2017
AI Learns Semantic Style Transfer
A new Two Minute Papers #177
Google’s DeepMind Is Now Capable of Creating Images from Your Sentences
Google's DeepMind team has developed a way for their AI to be able to create images from sentences. The more detailed the sentence, the more detailed the resulting image will be.
June 17, 2017
AI Learns To Create User Interfaces (pix2code) | Two Minute Papers #161
Two Minute Papers has a new video about creating GUI's using a neural network.
What convolutional neural networks see
Gene Kogan has produced a video to help see what is happening in the layers of a neural network
AI Makes Stunning Photos From Your Drawings (pix2pix)
Károly Zsolnai-Fehér produced this video about Image-to-Image Translation with Conditional Adversarial Nets.
The authors: Phillip Isola, Jun-Yan Zhu, Tinghui Zhou, Alexei A. Efros
Generative Visual Manipulation on the Natural Image Manifold
"Generative Visual Manipulation on the Natural Image Manifold", Jun-Yan Zhu, Philipp Krähenbühl, Eli Shechtman and Alexei A. Efros. In European Conference on Computer Vision (ECCV). 2016
Sept 13, 2016
NIPS 2016 - Generative Adversarial Networks - Ian Goodfellow
Ian Goodfellow speaking at the 2016 NIPS conference
AI Learns to Synthesize Pictures of Animals | Two Minute Papers
Károly Zsolnai-Fehér has another marvelous production.
TensorFlow Frontiers (Google I/O '17) Google Developers Google Developers
TensorFlow is an open-source machine learning (ML) platform that is fast, flexible, and production-ready. We'll cover recent advances in the TensorFlow ecosystem with a focus on performance.
VR and AR at Google (Google I/O '17)
Daydream is high-quality mobile VR for everyone, and Tango enables mobile devices to see the world like we do. Learn more about what we've built, what we've learned, and where we're headed.
Ian Goodfellow- Machine Learning Privacy and Security AIWTB 2017
Ian Goodfellow joins WTB once more for a talk on Machine Learning Privacy and Security! He is a staff research scientist at Google Brain. He is the lead author of the MIT Press textbook Deep Learning (www.deeplearningbook.org) and the inventor of generative adversarial networks. He is generally interested in all things deep learning, and usually focuses on generative models, machine learning security, and differential privacy.
Nicolas Papernot & Patrick McDaniel- Adversarial Examples in Machine Learning AIWTB 2017
Nicolas Papernot, Director of Institute for Network and Security Research, and Patrick McDaniel, Computer Security Graduate Research Assistant & Google PhD Fellow, come from Penn State University to show us adversarial examples and how they affect other models.
GTC 2017: Nvidia gpu technology conference Tesla V100 Volta
This is a recording of the GTC 2017 livestream.
Generative Models- Open AI blog post
This post describes four projects that share a common theme of enhancing or using generative models, a branch of unsupervised learning techniques in machine learning. In addition to describing our work, this post will tell you a bit more about generative models: what they are, why they are important, and where they might be going.
Andrej Karpathy, Pieter Abbeel, Greg Brockman, Peter Chen, Vicki Cheung, Rocky Duan, Ian Goodfellow, Durk Kingma, Jonathan Ho, Rein Houthooft, Tim Salimans, John Schulman, Ilya Sutskever, and Wojciech Zaremba. May 5,2017
Ian Goodfellow Generative Adversarial Networks
Ian Goodfellow talks at Generative adversarial networks (GANs) are a recently introduced class of generative models, designed to produce realistic samples.
Generative Adversarial Networks for Style Transfer (LIVE)
Siraj Raval holds a live stream on GANS May 3 2017
Generative Models is on the air. For over 4 months, we have been spending evenings looking with amazement at what is happening. The potential for impact, disruption and consequence outstrips the web's beginning. So when we found that the domain name was available, we wanted to try document our learning travels. Generative Models will attempt to be an source for generative neural networks. We will announce the best curated content for learning and experimenting with generative neural networks. Keeping up with just this segment of neural networks will be a big task. We will use collective curation to achieve these goals. The video Understand collective curation in under 90 seconds helps to describe the modus operandi.