The NVIDIA Deep Learning GPU Training System (DIGITS) puts the power of deep learning in the hands of data scientists rxnd researchers. Using DIGITS you can perform common deep learning tasks such as managing data, defining networks, training several models in parallel, monitoring training performance in real time, and choosing the best model from the results browser.
It's 2014 and I feel entitled to a good experience connecting to a remote server, instead the default still feels like telnet. After searching for quite a long time, I finally built my dream setup. These were the requirements: I want a single window/tab/panel of the terminal I'm
We aim to detect all instances of a category in an image and, for each instance, mark the pixels that belong to it. We call this task Simultaneous Detection and Segmentation (SDS). Unlike classical bounding box detection, SDS requires a segmentation and not just a box.
What I love about working at Google is the opportunity to harness cutting-edge machine intelligence for users' benefit. Two recent Research Blog posts talked about how we've used machine learning in the form of deep neural networks to improve voice search and YouTube thumbnails.
Andrej Karpathy's "NeuralTalk" code github.com/karpathy/neuraltalk2 slightly modified to run from a webcam feed. I recorded this live while walking near the bridge at Damstraat and Oudezijds Voorburgwal in Amsterdam.
Lecture: Chaos Communication Camp In August of 2011, I delivered a lecture (live video stream here) at Chaos Communication Camp in Finowfurt, Germany. The camp, held once every four years, is "an international, five-day open-air event for hackers and associated life-forms“ which provides a ”relaxed atmosphere for free exchange of technical, social, and political ideas".