Profile

Cover photo
Daniel Nouri
Lives in Berlin
1,223 followers|121,593 views
AboutPostsPhotosYouTube

Stream

This is a hands-on tutorial on deep learning. Step by step, we'll go about building a solution for the Facial Keypoint Detection Kaggle challenge. The tutorial introduces Lasagne, a new library for building neural networks with Python and Theano. We'll use Lasagne to implement a couple of ...
48
11
daniel rich's profile photoVINZ GIRAUDON's profile photoHao Wooi Lim's profile photoMohammad Havaei's profile photo
4 comments
 
Very cool. Concerning data augmentation have you tried image rotations? How that could be implemented?
Add a comment...

Daniel Nouri

Shared publicly  - 
 
 
Animal species are going extinct anywhere from 100 to 1,000 times the rates that would be expected under natural conditions. According to Elizabeth Kolbert's The Sixth Extinction and other recent studies, the increase results from a variety of human-caused effects including climate change, habitat destruction, and species displacement. Today's extinction rates rival those during the mass extinction event that wiped out the dinosaurs 65 million years ago.
Animals are dying out at a rate that rivals the dinosaur era. We catalogued the species at risk.
View original post
1
1
Mathieu Lonjaret's profile photo
Add a comment...

Daniel Nouri

Shared publicly  - 
 
 
This summer, I’m interning at Spotify in New York City, where I’m working on content-based music recommendation using convolutional neural networks. I wrote a blog post to explain my approach and show some preliminary results.
4 comments on original post
1
Add a comment...

Daniel Nouri

Shared publicly  - 
 
 
Deep content-based music recommendation

We trained a latent factor model on listening data from one million users for just under 400k songs, and then trained a deep convolutional neural network to predict the latent factors from audio. We showed that we can make sensible recommendations using these predicted factors, despite the large semantic gap between the characteristics of a song that affect user preference and the corresponding audio signal. We used the Million Song Dataset for this work.

Below is a t-SNE visualization of the distribution of predicted usage patterns, using latent factors predicted from audio. A few close-ups show artists whose songs are projected in specific areas. 

We will be demonstrating our approach at NIPS 2013: users will be able to specify YouTube clips. The demo will predict factors for these clips and try to find other clips with similar predicted usage patterns in a large database of 600,000 songs (a subset of the Million Song Dataset).

This is work with +Aäron van den Oord and +Benjamin Schrauwen

Paper: http://bit.ly/1csNpuG
Demo link: https://nips.cc/Conferences/2013/Program/event.php?ID=4174
6 comments on original post
6
1
Eric Casteleijn's profile photo
Add a comment...
 
So here's my little ConvNet Twitter bot that will classify your wildflower images; tell you which species you're looking at.  It currently knows around 150 flowers, mostly from Central Europe.  Use Twitter's built-in media upload and address the bot in your tweet using its name "@WildflowerID" to get an answer.
The latest from Wildflower bot (@WildFlowerID). Send me a pic of a wild flower, and I tell you which one it is. I currently know about 150 species from *Central Europe*. I'm a bot made by @dnouri and Teemu. Berlin
5
Add a comment...
 
So here's my little ConvNet Twitter bot that will classify your wildflower images; tell you which species you're looking at.  It currently knows around 150 flowers, mostly from Central Europe.  Use Twitter's built-in media upload and address the bot in your tweet using its name "@WildflowerID" to get an answer.
The latest from Wild Flower ID (@WildFlowerID). Send me a pic of a wild flower, and I tell you which one it is. I currently know about 150 species from Central Europe. I'm a bot made by Daniel and Teemu. Berlin
18
7
Za J's profile photoolgert denas's profile photonguyen duc tuan's profile photoJohn Illingworth's profile photo
6 comments
 
+John Taylor I'll have to think about how to best get feedback from people.  I was thinking about making a little website where I record the location of each photo (if available) and then present them on a map.  So that you could see who found what where.  And then people could provide structured feedback on that same website on whether the classification was correct.

Regarding the clicks, I've fixed a bug in the bot where it wasn't properly replying.  Now with that fixed, when you click on either the tweet with the image, or WildflowerID's response, you should see the complete thread with request (the image) and answer.
Add a comment...
Have him in circles
1,223 people
Simon Davies's profile photo
Torkel Lyng's profile photo
Chad Cunningham's profile photo
Stefan Blumenthal's profile photo
Uwe Seher's profile photo
Julian Rajendram's profile photo
Helge Tesdal's profile photo
Raphaël Barzic's profile photo
jerry xiong's profile photo

Daniel Nouri

Shared publicly  - 
 
 
Learning to Execute and Neural Turing Machines

I'd like to draw your attention to two papers that have been posted in the last few days from some of my colleagues at Google that I think are pretty interesting and exciting:

  Learning to Execute: http://arxiv.org/abs/1410.4615

  Neural Turing Machines: http://arxiv.org/abs/1410.5401

The first paper, "Learning to Execute", by +Wojciech Zaremba and +Ilya Sutskever attacks the problem of trying to train a neural network to take in a small Python program, one character at a time, and to predict its output.  For example, as input, it might take:

"i=8827
c=(i-5347)
print((c+8704) if 2641<8500 else 5308)"

During training, the model is given that the desired output for this program is "12185".  During inference, though, the model is able to generalize to completely new programs and does a pretty good of learning a simple Python interpreter from examples.


The second paper, "Neural Turing Machines", by +alex graves, Greg Wayne, and +Ivo Danihelka from Google's DeepMind group in London, couples an external memory ("the tape") with a neural network in a way that the whole system, including the memory access, is differentiable from end-to-end.  This allows the system to be trained via gradient descent, and the system is able to learn a number of interesting algorithms, including copying, priority sorting, and associative recall.

Both of these are interesting steps along the way of having systems learn more complex behavior, such as learning entire algorithms, rather than being used for just learning functions.

(Edit: changed link to Learning to Execute paper to point to the top-level Arxiv HTML page, rather than to the PDF).
Abstract: We extend the capabilities of neural networks by coupling them to external memory resources, which they can interact with by attentional processes. The combined system is analogous to a Turing Machine or Von Neumann architecture but is differentiable end-to-end, allowing it to be ...
19 comments on original post
2
Add a comment...
 
 
Oh, boy! NVIDIA launches cuDNN, a GPU accelerated Deep Neural Networks library. It's already available with Caffe v1.0
Machine Learning (ML) has its origins in the field of Artificial Intelligence, which started out decades ago with the lofty goals of creating a computer that could do any work a human can do.  Whil...
2 comments on original post
1
Add a comment...

Daniel Nouri

Shared publicly  - 
 
 
Chris Olah has written a brief but beautiful and pedagogical tutorial on the principles, motivations and amazing results obtained with word embeddings. This is a must-read for those who are newly interested in deep learning for NLP and also worth reading for the experts.
http://colah.github.io/posts/2014-07-NLP-RNNs-Representations/
Introduction. In the last few years, deep neural networks have dominated pattern recognition. They blew the previous state of the art out of the water for many computer vision tasks. Voice recognition is also moving that way. But despite the results, we have to wonder… why do they work so well?
7 comments on original post
1
Add a comment...
 
 
I'll be talking about classifying galaxies with deep learning at the Machine Learning meetup in Berlin next Tuesday. It will be a remote presentation seeing as I'm in New York for the summer.
1. Classifying galaxies with deep learning (Sander Dieleman, 45min) Deep learning has become a very popular approach for solving computer vision problems in recent years, with record-breaking results in object classification and detection. In this talk we'll explore a different but related application: galaxy morphology prediction. By automatically classifying galaxies based on their shape, astronomers can come to new insights about their origin...
View original post
1
Add a comment...

Daniel Nouri

Shared publicly  - 
 
So here's my little ConvNet Twitter bot that will classify your wildflower images; tell you which species you're looking at.  It currently knows around 150 flowers, mostly from Central Europe.  Use Twitter's built-in media upload and address the bot in your tweet using its name "@WildflowerID" to get an answer.
The latest from Wild Flower ID (@WildFlowerID). Send me a pic of a wild flower, and I tell you which one it is. I currently know about 150 species from Central Europe. I'm a bot made by Daniel and Teemu. Berlin
4
2
Mathieu Lonjaret's profile photoНиколай Алещанов's profile photo
Add a comment...

Daniel Nouri

Shared publicly  - 
 
Meanwhile the Ukrainian State Security Service says toxic chemicals were used in the Trade Unions House fire, and the violence was orchestrated and financed from outside with the connivance of local police who, along with emergency services, did not arrive at Kulykove Pole Square until hours after the clashes began.
1
Add a comment...
People
Have him in circles
1,223 people
Simon Davies's profile photo
Torkel Lyng's profile photo
Chad Cunningham's profile photo
Stefan Blumenthal's profile photo
Uwe Seher's profile photo
Julian Rajendram's profile photo
Helge Tesdal's profile photo
Raphaël Barzic's profile photo
jerry xiong's profile photo
Places
Map of the places this user has livedMap of the places this user has livedMap of the places this user has lived
Currently
Berlin
Previously
Innsbruck - Porto - Rotterdam - Den Haag - Copenhagen
Story
Tagline
Machine Learning, Analytics, Software Development
Basic Information
Gender
Male