Strange Beast, Una Especie De Mini Capítulo De “Black Mirror” Sobre El Futuro Inmediato Y El Tema

Interesting Papers for Week 28, 2017

When do correlations increase with firing rates in recurrent networks? Barreiro, A. K., & Ly, C. (2017). PLOS Computational Biology, 13(4), e1005506.

Consequences of the Oculomotor Cycle for the Dynamics of Perception. Boi, M., Poletti, M., Victor, J. D., & Rucci, M. (2017). Current Biology, 27(9), 1268–1277.

The Head-Direction Signal Plays a Functional Role as a Neural Compass during Navigation. Butler, W. N., Smith, K. S., van der Meer, M. A. A., & Taube, J. S. (2017). Current Biology, 27(9), 1259–1267.

Predicting explorative motor learning using decision-making and motor noise. Chen, X., Mohr, K., & Galea, J. M. (2017). PLOS Computational Biology, 13(4), e1005503.

Feedback Synthesizes Neural Codes for Motion. Clarke, S. E., & Maler, L. (2017). Current Biology, 27(9), 1356–1361.

Direct Brain Stimulation Modulates Encoding States and Memory Performance in Humans. Ezzyat, Y., Kragel, J. E., Burke, J. F., Levy, D. F., Lyalenko, A., Wanda, P., … Pedisich, I. (2017). Current Biology, 27(9), 1251–1258.

A map of abstract relational knowledge in the human hippocampal–entorhinal cortex. Garvert, M. M., Dolan, R. J., & Behrens, T. E. (2017). eLife, 6(e17086).

Sequential sensory and decision processing in posterior parietal cortex. Ibos, G., & Freedman, D. J. (2017). eLife, 6(e23743).

Active Dentate Granule Cells Encode Experience to Promote the Addition of Adult-Born Hippocampal Neurons. Kirschen, G. W., Shen, J., Tian, M., Schroeder, B., Wang, J., Man, G., … Ge, S. (2017). Journal of Neuroscience, 37(18), 4661–4678.

Subsampling scaling. Levina, A., & Priesemann, V. (2017). Nature Communications, 8, 15140.

Noise-enhanced coding in phasic neuron spike trains. Ly, C., & Doiron, B. (2017). PLOS ONE, 12(5), e0176963.

Spatial working memory alters the efficacy of input to visual cortex. Merrikhi, Y., Clark, K., Albarran, E., Parsa, M., Zirnsak, M., Moore, T., & Noudoost, B. (2017). Nature Communications, 8, 15041.

Brain networks for confidence weighting and hierarchical inference during probabilistic learning. Meyniel, F., & Dehaene, S. (2017). Proceedings of the National Academy of Sciences of the United States of America, 114(19), E3859–E3868.

Statistical learning in social action contexts. Monroy, C., Meyer, M., Gerson, S., & Hunnius, S. (2017). PLOS ONE, 12(5), e0177261.

Saccadic eye movements impose a natural bottleneck on visual short-term memory. Ohl, S., & Rolfs, M. (2017). Journal of Experimental Psychology: Learning, Memory, and Cognition, 43(5), 736–748.

Correlates of Perceptual Orientation Biases in Human Primary Visual Cortex. Patten, M. L., Mannion, D. J., & Clifford, C. W. G. (2017). Journal of Neuroscience, 37(18), 4744–4750.

Medial Entorhinal Cortex Selectively Supports Temporal Coding by Hippocampal Neurons. Robinson, N. T. M., Priestley, J. B., Rueckemann, J. W., Garcia, A. D., Smeglin, V. A., Marino, F. A., & Eichenbaum, H. (2017). Neuron, 94(3), 677–688.e6.

Towards a theory of cortical columns: From spiking neurons to interacting neural populations of finite size. Schwalger, T., Deger, M., & Gerstner, W. (2017). PLOS Computational Biology, 13(4), e1005507.

Homeostatic Plasticity Shapes Cell-Type-Specific Wiring in the Retina. Tien, N.-W., Soto, F., & Kerschensteiner, D. (2017). Neuron, 94(3), 656–665.e4.

Robust information propagation through noisy neural circuits. Zylberberg, J., Pouget, A., Latham, P. E., & Shea-Brown, E. (2017). PLOS Computational Biology, 13(4), e1005497.

#BlueOrigin test launch was a success! | Our audience: #djiphantom4 #djiglobal #uav #yuneec #hexacopter #djiinspire1 #quadcopter #miniquad #affiliatemarketing #robotics #robot #amazon #fpv #drones #aerialphotography #amazonprime #robots #djiphantom #arduino #drone #tesla #elonmusk #rcplane #spacex #sparkfun #nasa #raspberrypi #mavicpro #jeffbezos via @theofficialblueorigin (at Van Horn, Texas)

Machine learning could finally crack the 4,000-year-old Indus script

After a century of failing to crack an ancient script, linguists turn to machines.

The ultimate puzzle!

Introducing SAMOA, an open source platform for mining big data streams.

https://github.com/yahoo/samoa

Machine learning and data mining are well established techniques in the world of IT and especially among web companies and startups. Spam detection, personalization and recommendations are just a few of the applications made possible by mining the huge quantity of data available nowadays. However, “big data” is not only about Volume, but also about Velocity (and Variety, 3V of big data).

The usual pipeline for modeling data (what “data scientists” do) involves taking a sample from production data, cleaning and preprocessing it to make it usable, training a model for the task at hand and finally deploying it to production. The final output of this process is a pipeline that needs to run periodically (and be maintained) in order to keep the model up to date. Hadoop and its ecosystem (e.g., Mahout) have proven to be an extremely successful platform to support this process at web scale.

However, no solution is perfect and big data is “data whose characteristics forces us to look beyond the traditional methods that are prevalent at the time”. The current challenge is to move towards analyzing data as soon as it arrives into the system, nearly in real-time.

For example, models for mail spam detection get outdated with time and need to be retrained with new data. New data (i.e., spam reports) comes in continuously and the model starts being outdated the moment it is deployed: all the new data is sitting without creating any value until the next model update. On the contrary, incorporating new data as soon as it arrives is what the “Velocity” in big data is about. In this case, Hadoop is not the ideal tool to cope with streams of fast changing data.

Distributed stream processing engines are emerging as the platform of choice to handle this use case. Examples of these platforms are Storm, S4, and recently Samza. These platforms join the scalability of distributed processing with the fast response of stream processing. Yahoo has already adopted Storm as a key technology for low-latency big data processing.

Alas, currently there is no common solution for mining big data streams, that is, for doing machine learning on streams on a distributed environment.

Enter SAMOA

SAMOA (Scalable Advanced Massive Online Analysis) is a framework for mining big data streams. As most of the big data ecosystem, it is written in Java. It features a pluggable architecture that allows it to run on several distributed stream processing engines such as Storm and S4. SAMOA includes distributed algorithms for the most common machine learning tasks such as classification and clustering. For a simple analogy, you can think of SAMOA as Mahout for streaming.

SAMOA is both a platform and a library. As a platform, it allows the algorithm developer to abstract from the underlying execution engine, and therefore reuse their code to run on different engines. It also allows to easily write plug-in modules to port SAMOA to different execution engines.

As a library, SAMOA contains state-of-the-art implementations of algorithms for distributed machine learning on streams. The first alpha release allows classification and clustering.

For classification, we implemented a Vertical Hoeffding Tree (VHT), a distributed streaming version of decision trees tailored for sparse data (e.g., text). For clustering, we included a distributed algorithm based on CluStream. The library also includes meta-algorithms such as bagging.

HOW DOES IT WORK?

An algorithm in SAMOA is represented by a series of nodes communicating via messages along streams that connect pairs of nodes (a graph). Borrowing the terminology from Storm, this is called a Topology. Each node in the Topology is a Processor that sends messages to a Stream. The user code that implements the algorithm resides inside a Processor. Figure 3 shows an example of a Processor joining two stream from two source Processors. Here is a code snippet to build such a topology in SAMOA.

TopologyBuilder builder; Processor sourceOne = new SourceProcessor(); builder.addProcessor(sourceOne); Stream streamOne = builder.createStream(sourceOne); Processor sourceTwo = new SourceProcessor(); builder.addProcessor(sourceTwo); Stream streamTwo = builder.createStream(sourceTwo); Processor join = new JoinProcessor(); builder.addProcessor(join).connectInputShuffle(streamOne).connectInputKey(streamTwo);

SWEET! HOW DO I GET STARTED?

1. Download SAMOA

git clone git@github.com:yahoo/samoa.git cd samoa mvn -Pstorm package

2. Download the Forest CoverType dataset.

wget "http://downloads.sourceforge.net/project/moa-datastream/Datasets/Classification/covtypeNorm.arff.zip" unzip covtypeNorm.arff.zip

Forest CoverType contains the forest cover type for 30 x 30 meter cells obtained from US Forest Service (USFS) Region 2 Resource Information System (RIS) data. It contains 581,012 instances and 54 attributes, and it has been used in several papers on data stream classification.

3. Download a simple logging library.

wget "http://repo1.maven.org/maven2/org/slf4j/slf4j-simple/1.7.2/slf4j-simple-1.7.2.jar"

4. Run an Example. Classifying the CoverType dataset with the VerticalHoeffdingTree in local mode.

java -cp slf4j-simple-1.7.2.jar:target/SAMOA-Storm-0.0.1.jar com.yahoo.labs.samoa.DoTask "PrequentialEvaluation -l classifiers.trees.VerticalHoeffdingTree -s (ArffFileStream -f covtypeNorm.arff) -f 100000"

The output will be a sequence of the evaluation metrics for accuracy, taken every 100,000 instances.

To run the example on Storm, please refer to the instructions on the wiki.

I WANT TO KNOW MORE!

For more information about SAMOA, see the README and the wiki on github, or post a question on the mailing list.

SAMOA is licensed under an Apache Software License v2.0. You are welcome to contribute to the project! SAMOA accepts contributions under an Apache style contributor license agreement.

Good luck! We hope you find SAMOA useful. We will continue developing the framework by adding new algorithms and platforms.

Gianmarco De Francisci Morales (gdfm@yahoo-inc.com) and Albert Bifet (abifet@yahoo.com) @ Yahoo Labs Barcelona

Robot uses deep learning and big data to write and play its own music

A marimba-playing robot with four arms and eight sticks is writing and playing its own compositions in a lab at the Georgia Institute of Technology. The pieces are generated using artificial intelligence and deep learning.

Researchers fed the robot nearly 5,000 complete songs — from Beethoven to the Beatles to Lady Gaga to Miles Davis — and more than 2 million motifs, riffs and licks of music. Aside from giving the machine a seed, or the first four measures to use as a starting point, no humans are involved in either the composition or the performance of the music.

继续阅读

Example-based Face Stylization - Web Demo

DCGI and Adobe Research have put up an online interactive demo of their stylized facial animation paper.

Just drag and drop an image with a face into it, select one of the styles on the right, hit ‘Submit’ and see what happens …

Try it out for yourself here

Your order is processing 💿 for Super Deluxe

Michael Conover: Information Visualization for Large-Scale Data Workflows

data geometry

memes

visual analysis of program structure

visual analysis of propaganda

compare last week’s analysis and share with colleagues

geom_bin2d rather than geom_point(alpha=...) in ggplot2

ggpairs

automated grading: in addition to unit testing, 1) parse syntax trees of submissions, 2) define edit distance between them, 3) induces a network structure, 4) identify clusters, 5) give feedback to a representative member of the cluster and cc: everyone else

Presented at SF Data Mining on Oct 9, 2013 The ability to instrument and interrogate data as it moves through a processing pipeline is fundamental to effecti… @vagabondjack reasonengine.wordpress.com

More than 400 U.S. school districts are using augmented reality to teach students. Is AR the future of education?

follow @the-future-now

Imaginary Soundscape

Online project from Qosmo generates ambient sounds to Google Streetview panoramas through Deep Learning processes, interpreting the visuals for appropriate sounds:

“Imaginary Soundscape” is a web-based sound installation, in which viewers can freely walk around Google Street View and immerse themselves into imaginary soundscape generated with deep learning models.

… Once trained, the rest was straightforward. For a given image from Google Street View, we can find the best-matched sound file from a pre-collected sound dataset, such that the output of SoundNet with the sound input is the most similar to the output of the CNN model for the image. As the sound dataset, we collected 15000 sound files from internet published under Creative Commons license and filtered with another CNN model on spectrogram trained to distinguish environmental/ambient sound from other types of audio (music, speech, etc.). 

You can try it out for yourself here, and find more background information here