Data is big
16.1K views | +16 today
Follow
 
Scooped by ukituki
onto Data is big
Scoop.it!

The Signal and the Noise

The Signal and the Noise | Data is big | Scoop.it
Stats guru and political forecaster Nate Silver reveals why most predictions fail, and shows how we can isolate a true "signal" from a universe of increasingly big and noisy data
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!

Automated and Unmysterious Machine Learning in Cancer Detection

Automated and Unmysterious Machine Learning in Cancer Detection | Data is big | Scoop.it
explanation_wrong <- explain(
test_wrong[1:6, -1],
explainer = explainer,
n_labels = 1,
n_features = 5,
kernel_width = 0.5)

plot_features(explanation_wrong)
more...
No comment yet.
Scooped by ukituki
Scoop.it!

Creating Interactive data visualization using Shiny App in R (with examples)

Creating Interactive data visualization using Shiny App in R (with examples) | Data is big | Scoop.it
Introduction to Shiny App & detailed explaination in UI.R & Server.R along with codes, hands on exercise with Loan Prediction practice problem
more...
No comment yet.
Scooped by ukituki
Scoop.it!

AlphaGo Zero Explained In One Diagram – Applied Data Science – Medium

AlphaGo Zero Explained In One Diagram – Applied Data Science – Medium | Data is big | Scoop.it
Download the AlphaGo Zero cheat sheet
more...
No comment yet.
Scooped by ukituki
Scoop.it!

Making Predictions over HTTP with R

Making Predictions over HTTP with R | Data is big | Scoop.it
Using R as a Production Machine Learning Language (Part I) Why is this necessary? Getting Started with Plumber on a trained model Prepping Data Train Model Evaluating Model Save model to RDS Building Plumber API Plumber API files First use of Plumber Annotation - Health check endpoint Landing Page Prediction Endpoint Putting it all together Concluding Remarks Using R as a Production Machine Learning Language (Part I) There’s often confusion amoung the data science and machine learning crowd about the quality of R as a production level language for deploying predictive models.
more...
No comment yet.
Scooped by ukituki
Scoop.it!

Routes to Defensibility for your AI Startup – Machine Learnings

Routes to Defensibility for your AI Startup – Machine Learnings | Data is big | Scoop.it
With little time, effort and funding, startups can get enough data to meet customers’ expectations. Hence the defensibility is relatively limited.
more...
No comment yet.
Scooped by ukituki
Scoop.it!

Marc Bellemare (Google Brain) – "A Distributional Perspective on Reinforcement Learning"

Abstract: This talk will present an overview of our recent research on distributional reinforcement learning. In a recent paper we argued for the fundamental importance…
more...
No comment yet.
Scooped by ukituki
Scoop.it!

Top 50 ggplot2 Visualizations - The Master List (With Full R Code)

Top 50 ggplot2 Visualizations - The Master List (With Full R Code) | Data is big | Scoop.it
R Language Tutorials for Advanced Statistics
more...
No comment yet.
Scooped by ukituki
Scoop.it!

Reinforcement Learning - A Simple Python Example and A Step Closer to AI with Assisted Q-Learning - YouTube

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

Tutorial to deploy Machine Learning models in Production as APIs (using Flask)

Tutorial to deploy Machine Learning models in Production as APIs (using Flask) | Data is big | Scoop.it
This article explains and provides step by step approach on how to deploy a machine learning model as an API using Flask - a Python web framework
more...
No comment yet.
Rescooped by ukituki from Deep_In_Depth : Data Science and Deep Learning
Scoop.it!

Activation Functions: Neural Networks

Activation Functions: Neural Networks | Data is big | Scoop.it
Sigmoid, tanh, Softmax, ReLU, Leaky ReLU EXPLAINED !!!

Via Eric Feuilleaubois
more...
No comment yet.
Scooped by ukituki
Scoop.it!

Becoming a 10x Data Scientist - Algorithmia

Becoming a 10x Data Scientist - Algorithmia | Data is big | Scoop.it
Borrowing tips and tricks from software developers, learn how to create a more productive workflow on the journey to becoming a 10X Data Scientist.
more...
No comment yet.
Scooped by ukituki
Scoop.it!

How to Learn Advanced Concepts Fast

How to Learn Advanced Concepts Fast | Data is big | Scoop.it
These are 10 strategies I use to learn advanced concepts as fast as possible! I'm going to explain each one, and give some examples of what I mean.
more...
No comment yet.
Scooped by ukituki
Scoop.it!

Effective Learning: The Near Future of AI

Effective Learning: The Near Future of AI | Data is big | Scoop.it
In this post, we have listed down the most promising Deep Learning techniques which will shape the future of AI in coming days.
more...
No comment yet.
Scooped by ukituki
Scoop.it!

GAN playground: Experiment with Generative Adversarial Networks in your browser

GAN Playground - Explore Generative Adversarial Nets in your Browser

ukituki's insight:
GAN Playground - Explore Generative Adversarial Nets in your Browser
more...
No comment yet.
Scooped by ukituki
Scoop.it!

Capsule Networks: An Improvement to Convolutional Networks - YouTube

Capsule Networks: An Improvement to Convolutional Networks
more...
No comment yet.
Scooped by ukituki
Scoop.it!

Feature selection with the Boruta Algorithm

Feature selection with the Boruta Algorithm | Data is big | Scoop.it
One of the most important steps in building a statistical model is deciding which data to include. With very large datasets and models that have a high computational cost, impressive efficiency can be realized by identifying the most (and least) useful features of a dataset prior to running a model. Feature selection is the process…
more...
No comment yet.
Scooped by ukituki
Scoop.it!

Reinforcement Learning Coach Documentation

Reinforcement Learning Coach Documentation | Data is big | Scoop.it
Train and evaluate reinforcement learning agents by harnessing the power of multi-core CPU processing to achieve state-of-the-art results. Provide a sandbox for easing the development process of new algorithms through a modular design and an elegant set of APIs.
more...
No comment yet.
Scooped by ukituki
Scoop.it!

[FoR&AI] The Seven Deadly Sins of Predicting the Future of AI – Rodney Brooks

[FoR&AI] The Seven Deadly Sins of Predicting the Future of AI – Rodney Brooks | Data is big | Scoop.it
more...
No comment yet.
Scooped by ukituki
Scoop.it!

Top 15 Evaluation Metrics for Classification Models

Top 15 Evaluation Metrics for Classification Models | Data is big | Scoop.it
Computing just the accuracy to evaluate a classification model is not enough. This tutorial shows how to build and interpret the evaluation metrics.
more...
No comment yet.
Scooped by ukituki
Scoop.it!

Pre-configured Amazon AWS deep learning AMI with Python - PyImageSearch

Pre-configured Amazon AWS deep learning AMI with Python - PyImageSearch | Data is big | Scoop.it
Ready to get started with deep learning? Use my pre-configured Ubuntu Amazon AMI to jump start your deep learning projects with Python, Keras, and more.
more...
No comment yet.
Scooped by ukituki
Scoop.it!

Command line tools for Machine learning

Command line tools for Machine learning | Data is big | Scoop.it
Preamble I thought I should make an article with my favourite tools that can be used from the command line and be run with minimal memory
more...
No comment yet.
Scooped by ukituki
Scoop.it!

Neural Network Zoo Prequel: Cells and Layers - The Asimov Institute

Neural Network Zoo Prequel: Cells and Layers - The Asimov Institute | Data is big | Scoop.it
Cells The Neural Network Zoo shows different types of cells and various layer connectivity styles, but it doesn’t really go into how each cell type works. A number of cell types I originally gave different colours to differentiate the networks more clearly, but I have since found out that these cells work more or less …
more...
No comment yet.