Sign in or Join FriendFeed
FriendFeed is the easiest way to share online. Learn more »
Microsoft Inductive User Interface Guidelines -
Roger Federer - Top 10 Amazing Gets (HD) - YouTube -
Roger Federer - Top 10 Amazing Gets (HD) - YouTube
Agre on what it means to be critical: to be aware of one's own biases, and the cultural assumptions one brings to something. He talks about close reading an AI text, and trying to understand all the sociological background. - Michael Nielsen
Music Animation Machine - YouTube -
Tera-scale deep learning - Quoc V. Le on Vimeo -
On the 2012 Google-Stanford deep learning paper. - Michael Nielsen
An Analysis of Single-Layer Networks in Unsupervised Feature Learning -
More learned features helps a lot; smaller stride length helps a lot. Larger local receptive fields barely helps at all. - Michael Nielsen
Classification datasets results -
Results for MNIST, CIFAR-10, CIFAR-100, STL-10 and SVHN - Michael Nielsen
Byron's Blog: Unlabeled Object Recognition in Google+ -
International Conference on Learning Representations (ICLR) 2013 | -
Best practices for convolutional neural networks applied to visual document analysis -
Simard, Steinkraus, and Platt on the value of image distortion and convolutional networks. - Michael Nielsen
Japanese children learn super-fast mathematics with abacus - YouTube -
Good interview with an online troll: "I am lucky to have not had people who liked me for who I was when I was truly awful" - Michael Nielsen
Exercise for depression | Cochrane Summaries -
How My Neural Net Sees Blackboards | Christopher Olah's Blog -
Chris uses neural nets to clean up handwritten blackboard images. - Michael Nielsen
Convolutional Deep Belief Networks for Scalable Unsupervised Learning of Hierarchical Representations - -
Honglak Lee's 2009 paper on hierarchical infererence in convolutional DBNs. - Michael Nielsen
ACM Web Science talk, as written | Quinn Said -
On the aesthetics of the network. - Michael Nielsen
[1003.0358] Deep Big Simple Neural Nets Excel on Handwritten Digit Recognition -
An example where we can use back-prop to train a deep net. - Michael Nielsen
26th Annual Conference on Neural Information Processing Systems (NIPS), Lake Tahoe 2012 - VideoLectures - -
Test Your Intuition (19): The Advantage of the Proposers in the Stable Matching Algorithm | Combinatorics and more -
Gil Kalai on the Gale-Shapley theorem. - Michael Nielsen
No More Pesky Learning Rates -
Bill Watterson's Speech - Kenyon College, 1990 -
Fernando Perez: "Literate computing" and computational reproducibility: IPython in the age of data-driven journalism -
The elements of statistical learning -
The Rise and Fall of Bitcoin | Wired Magazine | -
What do readers want from frontmatter and endmatter? — Chocolate and Vodka -
IPAM: Deep Learning, Feature Learning -
Summer School lectures - Michael Nielsen
CERN Chooses Coverity to Ensure Accuracy of Large Hadron Collider Software - Coverity -
Coverity found 40,000 defects in the LHC's code. - Michael Nielsen
Structure and Interpretation of Computer Programs, Video Lectures -
The Mother of All Demos, presented by Douglas Engelbart (1968) - YouTube -
The Mother of All Demos, presented by Douglas Engelbart (1968) - YouTube
Other ways to read this feed:Feed readerFacebook