Profile cover photo
Profile photo
Xiang Zhang
275 followers -
I have gone mad.
I have gone mad.

275 followers
About
Posts

Post has shared content
AI bots / agents are trendy! DeepMind Lab is now open source. Three successive announcements; TorchCraft, Universe and DeepMind Lab...
Add a comment...

Post has shared content
The Deep Learning book from Goodfellow, Bengio and Courville is out in hard copy at MIT Press and on Amazon.
Add a comment...

Post has shared content
I am extremely happy to finally see this paper published. This is a very encouraging result showing that a deep neural network trained on many retina images can perform as well as a human ophthalmologist.

In India, millions of people are already severely affected by this disease and a large portion become permanently blind because there is not enough doctors to diagnose it early or because the diagnostic cost is too high. Automating such diagnostic could greatly increase the number of people that can be treated before they become blind.

I had the chance to be involved as a technical advisor early on in the project when I was still in the Street View team because it turns out that some of the techniques we used then to update Google Maps using Street View images and neural networks could be applied for this medical problem.

Being able to reuse deep learning techniques for very different domains such as mapping and medical imaging is one of the main reasons why Deep Learning is growing & improving rapidly. Any improvements done on core vision models positively impact all these applications. And the more applications there are, the more incentives there are to improve such techniques, and the more people work on them.

https://www.wired.com/2016/11/googles-ai-reads-retinas-prevent-blindness-diabetics/
Add a comment...

Post has shared content
Today, we're releasing two large datasets for robotics research:

Grasping: A collection of 650k grasp attempts, data used in: http://arxiv.org/abs/1603.02199

Push: A collection of 59k examples of pushing motions, data used in: http://arxiv.org/abs/1605.07157

Both datasets contain RGB-D views of the arm, gripper and objects, along with actuation and position parameters. They were collected in a controlled environment using a wide collection of everyday objects, some of which were held out for evaluation. Enjoy!

Credits: +Sergey Levine, +Chelsea Finn and +Laura Downs.
Add a comment...

Post has attachment
Thunder is now v0.3.0!
Add a comment...

Post has shared content

Post has shared content
Facebook unveiled what it's dubbed DeepText, a deep-learning-based engine designed to read and understand users' posts and comments.
Add a comment...

Post has shared content

Post has shared content
After the release of DCGAN (and code), which is a neural network that can generate natural images (collaboration between Alec Radford, Luke Metz and me), people from the community have generated their own manga characters, flowers and now their own letters from reading chinese books. Fun stuff. All these generations are the hallucinations of a neural network and are not real.

Our paper: http://arxiv.org/abs/1511.06434
Our code:
https://github.com/Newmu/dcgan_code (Theano)
https://github.com/soumith/dcgan.torch (Torch)
https://github.com/mattya/chainer-DCGAN (manga)
http://genekogan.com/works/a-book-from-the-sky.html (chinese characters)
https://twitter.com/vintermann/status/675599478494208000 (flowers)
Looking for more fun stuff from the community.
PhotoPhotoPhotoPhotoPhoto
12/15/15
6 Photos - View album
Add a comment...

Post has attachment
Not that I was even a bit convinced by his arguments, Roger Penrose's classic book "The Emperor's New Mind" is definitely worth reading, even if it was just for the vast scope of knowledge it contains. It has been a very enjoyable journey on the opposite of what I believe. He also has two later books of the same string of thought, which I am looking forward to reading.
Add a comment...
Wait while more posts are being loaded