Data is big
Follow
Find
2.1K views | +1 today
 
Scooped by ukituki
onto Data is big
Scoop.it!

Academic Papers | Kaggle

Academic Papers | Kaggle | Data is big | Scoop.it
Kaggle is a platform for data prediction competitions. Companies, organizations and researchers post their data and have it scrutinized by the world's best statisticians.
more...
No comment yet.
Data is big
"The future is here. It's just not evenly distributed yet." William Gibson
Curated by ukituki
Your new post is loading...
Your new post is loading...
Scooped by ukituki
Scoop.it!

Machine Learning Algorithm Studying Fine Art Paintings Sees Things Art Historians Had Never Noticed

Machine Learning Algorithm Studying Fine Art Paintings Sees Things Art Historians Had Never Noticed | Data is big | Scoop.it
Artificial intelligence reveals previously unrecognised influences between great artists
more...
No comment yet.
Scooped by ukituki
Scoop.it!

Harvard Unleashes Swarm of Robots

Harvard Unleashes Swarm of Robots | Data is big | Scoop.it
Harvard University scientists have developed a thousand tiny robots that, like swarming bees or army ants, can work together in vast numbers without a guiding central intelligence, in the largest team so far of self-organizing mobile robots. Photo: Michael Rubenstein, Harvard University.
more...
No comment yet.
Scooped by ukituki
Scoop.it!

A Conversation with Hadley Wickham – the useR! 2014 interview

A Conversation with Hadley Wickham – the useR! 2014 interview | Data is big | Scoop.it
Hadley Wickham is famous. He’s not Kardashian famous, but walking around useR! and seeing the community’s reaction to him, there’s no question, he’s ‘R famous’.
more...
No comment yet.
Scooped by ukituki
Scoop.it!

Learning from the best Kagglers

Learning from the best Kagglers | Data is big | Scoop.it
Guest contributor David Kofoed Wind is a PhD student in Cognitive Systems at The Technical University of Denmark (DTU): As a part of my master's thesis on competitive machine learning, I talked to ...
more...
No comment yet.
Scooped by ukituki
Scoop.it!

Deep Learning in Neural Networks: An Overview

ukituki's insight:
In recent years, deep artificial neural networks (including recurrent ones) have won numerous contests in pattern recognition and machine learning. This historical survey compactly summarises relevant work, much of it from the previous millennium. Shallow and deep learners are distinguished by the depth of their credit assignment paths, which are chains of possibly learnable, causal links between actions and effects. I review deep supervised learning (also recapitulating the history of backpropagation), unsupervised learning, reinforcement learning & evolutionary computation, and indirect search for short programs encoding deep and large networks.
  
more...
No comment yet.
Scooped by ukituki
Scoop.it!

Kaggle Competition Past Solutions | Garbled Notes

ukituki's insight:

This is a gold mine!

more...
No comment yet.
Scooped by ukituki
Scoop.it!

Shiny - Save your app as a function

Shiny - Save your app as a function | Data is big | Scoop.it
more...
No comment yet.
Scooped by ukituki
Scoop.it!

Extreme Learning Machine: Learning Without Iterative Tuning

Neural networks (NN) and support vector machines (SVM) play key roles in machine learning and data analysis. However, it is known that there exist some challenging issues with them such as...
more...
No comment yet.
Scooped by ukituki
Scoop.it!

The infinite MNIST dataset

The infinite MNIST dataset | Data is big | Scoop.it
ukituki's insight:

This code produces an infinite supply of digit images derived from the well known MNIST dataset using pseudo-random deformations and translations. This is a streamlined version of the code used for the experiments reported in (Loosli, Canu, Bottou, 2007). A subset of the examples generated by this code are known as MNIST8M.  

more...
No comment yet.
Scooped by ukituki
Scoop.it!

How to implement an algorithm from a scientific paper | Code Capsule

How to implement an algorithm from a scientific paper | Code Capsule | Data is big | Scoop.it
This article is a short guide to implementing an algorithm from a scientific paper. I have implemented many complex algorithms from books and scientific
more...
No comment yet.
Scooped by ukituki
Scoop.it!

Quoc Le’s Lectures on Deep Learning | Gaurav Trivedi

more...
No comment yet.
Scooped by ukituki
Scoop.it!

Radim Řehůřek : Word2vec Tutorial

Radim Řehůřek : Word2vec Tutorial | Data is big | Scoop.it
I never got round to writing a tutorial on how to use word2vec in gensim. It s simple enough and the API docs are straightforward, but I know some people prefer more verbose formats. Let this post be a tutorial and a reference example.
more...
No comment yet.
Scooped by ukituki
Scoop.it!

Tutorials from useR! 2014 Los Angeles conference

Tutorials from useR! 2014 Los Angeles conference | Data is big | Scoop.it
The annual useR! international R User conference is the main meeting of the R user and developer community. In 2014, the conference will be held at the campus of the University of California in Los Angeles (UCLA).
more...
No comment yet.
Scooped by ukituki
Scoop.it!

So you wanna try Deep Learning? - Exchangeable random experiments

So you wanna try Deep Learning? - Exchangeable random experiments | Data is big | Scoop.it
I’m keeping this post quick and dirty, but at least it’s out there. The gist of this post is that I put out a one file gist that does all the basics …
more...
No comment yet.
Scooped by ukituki
Scoop.it!

Max Kuhn Interviewed by DataScience.LA at useR - YouTube

ukituki's insight:

Data Scientist, Author ("Applied Predictive Modeling" with Kjell Johnson) and R caret package developer Max Kuhn sits down for an in-depth interview with Eduardo Arino de la Rubia. They discuss the art and science of Predictive Modeling in the real world, the multifaceted R caret package, the pluses and perils of programming in R and much more.

more...
No comment yet.
Scooped by ukituki
Scoop.it!

First-person Hyperlapse Videos

First-person Hyperlapse Videos | Data is big | Scoop.it
ukituki's insight:
Algo for turning boring first-person perspective videos into the attractive time lapses.
more...
No comment yet.
Scooped by ukituki
Scoop.it!

Markov Chains #visualization

Markov chains, named after Andrey Markov, are mathematical systems that hop from one "state" (a situation or set of values) to another. For example, if you made a Markov chain model of a baby's behavior, you might include "playing," "eating", "sleeping," and "crying" as states, which together with other behaviors could form a 'state space': a list of all possible states. In addition, on top of the state space, a Markov chain tells you the probabilitiy of hopping, or "transitioning," from one state to any other state---e.g., the chance that a baby currently playing will fall asleep in the next five minutes without crying first.

ukituki's insight:

Markov chains, named after Andrey Markov, are mathematical systems that hop from one "state" (a situation or set of values) to another. For example, if you made a Markov chain model of a baby's behavior, you might include "playing," "eating", "sleeping," and "crying" as states, which together with other behaviors could form a 'state space': a list of all possible states. In addition, on top of the state space, a Markov chain tells you the probabilitiy of hopping, or "transitioning," from one state to any other state---e.g., the chance that a baby currently playing will fall asleep in the next five minutes without crying first.

more...
No comment yet.
Scooped by ukituki
Scoop.it!

Learning more like a human: 18 free eBooks on Machine Learning

Learning more like a human: 18 free eBooks on Machine Learning | Data is big | Scoop.it

Machine Learning is a type of artificial intelligence (AI) that provides computer programs with the ability to learn, grow and change when exposed to new data, without being explicitly programmed. Here, we present 20 free eBooks on Machine Learning, which will guide you to understand more about Machine Learning.

more...
No comment yet.
Scooped by ukituki
Scoop.it!

Understanding Random Forests: From Theory to Practice

Understanding Random Forests: From Theory to Practice | Data is big | Scoop.it
more...
No comment yet.
Scooped by ukituki
Scoop.it!

15 interviews with 15 data scientists

15 interviews with 15 data scientists | Data is big | Scoop.it

Interesting PDF document featuring 15 data scientists (mostly co-founders of various start-ups or well known data science websites), with an average of 9 pages  per interview. 

ukituki's insight:
Parham Aarabi: Visual Image Extraction - CEO of ModiFace & University of Toronto Professor Pete Warden: Object Recognition - Co-Founder & CTO of Jetpac Trey Causey: Data Science & Football - Founder of the spread, Data Scientist at zulily Ravi Parikh: Modernizing Web and iOS Analytics - Co-Founder of Heap Analytics (YC W13) Ryan Adams: Intelligent Probabilistic Systems - Leader of Harvard Intelligent Probabilistic Systems Group Kang Zhao: Machine Learning & Online Dating - Assistant Professor, Tippie College of Business, University of Iowa Dave Sullivan: Future of Neural Networks and MLaaS - Founder and CEO of Blackcloud BSG - company behind Ersatz Wolfgang van Loeper: Big Data & Agriculture - Founder & CEO of MySmartFarm Laura Hamilton: Predicting Hospital Readmissions - Founder & CEO of Additive Analytics Harlan Harris: Building a Data Science Community - Founder and President of Data Community DC Abe Gong: Using Data Science to Solve Human Problems - Data Scientist at Jawbone, DataScienceWeekly.orgK. Hensien & C. Turner: ML => Energy Efficiency - Senior Product Development at Optimum Energy, Data Scientist at The Data Guild Andrej Karpathy: Training DL Models in a Browser - Machine Learning PhD student at Stanford, Creator of ConvNetJS George Mohler: Predictive Policing - Chief Scientist at PredPol, Asst. Professor Mathematics & CS, Santa Clara University Carl Anderson: Data Science & Online Retail - Director of Data Science at Warby Parker
more...
No comment yet.
Scooped by ukituki
Scoop.it!

Data Analytics and Visualisation

Data Analytics and Visualisation | Data is big | Scoop.it
data visualisation examples data-analytics.github.io Selected Tools is a collection of tools that worls for the people on a daily basis and recommend warmly.
more...
No comment yet.
Scooped by ukituki
Scoop.it!

Caffe - deep learning framework developed with cleanliness, readability, and speed in mind.

ukituki's insight:

Caffe already powers academic research projects, startup prototypes, and even large-scale industrial applications in vision, speech, and multimedia. There is an active discussion and support community on Github.

more...
No comment yet.
Scooped by ukituki
Scoop.it!

Understanding Convolutions - colah's blog

Understanding Convolutions - colah's blog | Data is big | Scoop.it
more...
No comment yet.
Scooped by ukituki
Scoop.it!

Data Structure Visualization

more...
No comment yet.
Scooped by ukituki
Scoop.it!

10 R Packages to Win Kaggle Competitions

10 R Packages to Win Kaggle Competitions | Data is big | Scoop.it
10 R Packages to Win Kaggle Competitions by Xavier Conort
more...
No comment yet.