Data is big
15.0K views | +0 today
Follow
 
Scooped by ukituki
onto Data is big
Scoop.it!

60+ R resources to improve your data skills

60+ R resources to improve your data skills | Data is big | Scoop.it
From books to videos to online tutorials -- most free! -- here are plenty of ideas to burnish your R knowledge.
more...
No comment yet.
Data is big
"The future is here. It's just not evenly distributed yet." - William Gibson     :::: Follow this topic for fresh resources and ideas related to Data Science, Machine Learning, Algorithms and #bigdata :::: <a href="http://www.dataisbig.co" rel="nofollow">http://www.dataisbig.co</a>/
Curated by ukituki
Your new post is loading...
Your new post is loading...
Scooped by ukituki
Scoop.it!

Neural networks for algorithmic trading. Multimodal and multitask deep learning

Neural networks for algorithmic trading. Multimodal and multitask deep learning | Data is big | Scoop.it
Here we are again! We already have four tutorials on financial forecasting with artificial neural networks where we compared different architectures for financial time series forecasting, realized…
more...
No comment yet.
Scooped by ukituki
Scoop.it!

120 Machine Learning business ideas from the latest McKinsey report.

120 Machine Learning business ideas from the latest McKinsey report. | Data is big | Scoop.it
Machine learning is on the edge of revolutionizing those 12 sectors. Most leaders in those industries look at Machine Learning and see a non-stable, none viable technology in the short term.
more...
No comment yet.
Scooped by ukituki
Scoop.it!

Zero to One — A Ton of Awe-Inspiring Deep Learning Demos with Code for Beginners

Zero to One — A Ton of Awe-Inspiring Deep Learning Demos with Code for Beginners | Data is big | Scoop.it
— said they wanted deep learning examples that they can just download and run. No Math. No Theory. No Books. It’s difficult to find deep learning examples that are open source and that also run first…
more...
No comment yet.
Scooped by ukituki
Scoop.it!

The Data Analyst: A Potential Difference Maker | The Higher Tempo Press

The Data Analyst: A Potential Difference Maker | The Higher Tempo Press | Data is big | Scoop.it

Believe or not, not everyone on The Higher Tempo is actually any good at the game. Take me for example. My save over on my own blog has spanned five seasons – it took me three just to get promoted and I got instantly relegated then couldn’t bounce right back up. 

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

Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour

Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour | Data is big | Scoop.it
In this paper, we empirically show that on the ImageNet dataset large minibatches cause optimization difficulties, but when these are addressed the trained networks exhibit good generalization.
ukituki's insight:
How long does it take to train the state-of-the-art imagenet model? The answer is one hour :) 

Yeah, remember when we just started with AlexNet it took a week, and our model has already grown like 10x bigger in the meantime too! So consider the "software Moore's Law" broken.
more...
No comment yet.
Scooped by ukituki
Scoop.it!

Deep Learning Challenges from a Kaggle Competition

Vladimir Iglovikov, Kaggle Master, talks about a Deep Learning approach to the "Dstl Satellite Imagery Feature Detection" competition, challenges an
more...
No comment yet.
Scooped by ukituki
Scoop.it!

Machine learning 10 - Funny pictures

Machine learning 10 - Funny pictures | Data is big | Scoop.it
The following are funny pictures related to machine learning or data science I found online. It is a great way to learn some concepts i
more...
No comment yet.
Scooped by ukituki
Scoop.it!

[1206.4634] Artist Agent: A Reinforcement Learning Approach to Automatic Stroke Generation in Oriental Ink Painting

Oriental ink painting, called Sumi-e, is one of the most appealing painting styles that has attracted artists around the world. Major challenges in computer-based Sumi-e simulation are to abstract complex scene information and draw smooth and natural brush strokes. To automatically find such strokes, we propose to model the brush as a reinforcement learning agent, and learn desired brush-trajectories by maximizing the sum of rewards in the policy search framework. We also provide elaborate design of actions, states, and rewards tailored for a Sumi-e agent. The effectiveness of our proposed approach is demonstrated through simulated Sumi-e experiments.
more...
No comment yet.
Scooped by ukituki
Scoop.it!

AudioSet

A large-scale dataset of manually annotated audio eventsAudioSet consists of an expanding ontology of 632 audio event classes and a collection of 2,084,320 human-labeled 10-second sound clips drawn from YouTube videos. The ontology is specified as a hierarchical graph of event categories, covering a wide range of human and animal sounds, musical instruments and genres, and common everyday environmental sounds. By releasing AudioSet, we hope to provide a common, realistic-scale evaluation task for audio event detection, as well as a starting point for a comprehensive vocabulary of sound events.
ukituki's insight:
A large-scale dataset of manually annotated audio events AudioSet consists of an expanding ontology of 632 audio event classes and a collection of 2,084,320 human-labeled 10-second sound clips drawn from YouTube videos.
more...
No comment yet.
Scooped by ukituki
Scoop.it!

Explaining the decisions of machine learning algorithms | StatsBlogs.com | All About Statistics

Explaining the decisions of machine learning algorithms | StatsBlogs.com | All About Statistics | Data is big | Scoop.it
more...
No comment yet.
Scooped by ukituki
Scoop.it!

My Curated List of AI and Machine Learning Resources from Around the Web

My Curated List of AI and Machine Learning Resources from Around the Web | Data is big | Scoop.it
When I was writing books on networking and programming topics in the early 2000s, the web was a good, but an incomplete resource. Blogging had started to take off, but YouTube wasn’t around yet, nor…
more...
No comment yet.
Scooped by ukituki
Scoop.it!

Deep Learning with R

Deep Learning with R | Data is big | Scoop.it
For R users, there hasn’t been a production grade solution for deep learning (sorry MXNET). This post introduces the Keras interface for R and how it can be used to
ukituki's insight:
Tensorflow and Keras finally find their way to the R world
more...
No comment yet.
Scooped by ukituki
Scoop.it!

Thinking of doing a machine learning PhD? Read this first.

Thinking of doing a machine learning PhD? Read this first. | Data is big | Scoop.it
We explain why it’s a high-impact area, how to work out if it’s for you, and exactly how and where to apply.
more...
No comment yet.
Scooped by ukituki
Scoop.it!

Redefining Basketball Positions with Unsupervised Learning

Redefining Basketball Positions with Unsupervised Learning | Data is big | Scoop.it
The NBA Finals are over. The last of the champagne bottles have been emptied and the confetti has begun to settle. Now that the Golden State Warriors have finished unleashing their otherworldly…
more...
No comment yet.
Scooped by ukituki
Scoop.it!

The MMC Ventures AI Investment Framework: 17 success factors for the age of AI

The MMC Ventures AI Investment Framework: 17 success factors for the age of AI | Data is big | Scoop.it

Artificial intelligence — specifically, machine learning (ML) — is a powerful ‘enabling technology’ that represents a paradigm shift in software capability.

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

The 5 Levels of Machine Learning Iteration

The 5 Levels of Machine Learning Iteration | Data is big | Scoop.it
Practical machine learning has a distinct cyclical nature that demands constant iteration, tuning, and improvement. We aim to showcase its beauty.
more...
No comment yet.
Scooped by ukituki
Scoop.it!

Everything that Works Works Because it's Bayesian: Why Deep Nets Generalize?

Everything that Works Works Because it's  Bayesian: Why Deep Nets Generalize? | Data is big | Scoop.it
The Bayesian community should really start going to ICLR. They really should have started going years ago. Some people actually have. For too long we Bayesians have, quite arrogantly, dismissed deep neural networks as unprincipled, dumb black boxes that lack elegance. We said that highly over-parametrised models fitted via maximum
more...
No comment yet.
Scooped by ukituki
Scoop.it!

Creating a Modern OCR Pipeline Using Computer Vision and Deep Learning

In this post we will take you behind the scenes on how we built a state-of-the-art Optical Character Recognition (OCR) pipeline for our mobile document scanner.
more...
No comment yet.
Scooped by ukituki
Scoop.it!

Robotics Institute Seminar Series - YouTube

Robotics Institute Seminar Series - YouTube | Data is big | Scoop.it
A seminar series hosted by Carnegie Mellon University's Robotics Institute.
ukituki's insight:
A seminar series hosted by Carnegie Mellon University's Robotics Institute.
more...
No comment yet.
Scooped by ukituki
Scoop.it!

ReinforcementLearning: A package for replicating human behavior in R

ReinforcementLearning: A package for replicating human behavior in R | Data is big | Scoop.it
Nicolas Proellochs and Stefan Feuerriegel 2017-04-06 Introduction Reinforcement learning has recently gained a great deal of traction in studies that call for
ukituki's insight:
Share your insight
more...
No comment yet.
Scooped by ukituki
Scoop.it!

Explained Visually

ukituki's insight:
Explained Visually (EV) is an experiment in making hard ideas intuitive inspired the work of Bret Victor's Explorable Explanations.
more...
No comment yet.