Every two weeks, we find the most interesting data science links from around the web and collect them in Data Science Briefings, the DataMiningApps newsletter. Subscribe now for free if you want to be the first to get up to speed on interesting resources.
- Improving YouTube video thumbnails with deep neural nets
The YouTube team explains how they trained a neural network to detect the best frame in a video to be used as a thumbnail.
- Visualizing Machine Learning Thresholds to Make Better Business Decisions
As data scientists, when we build a machine learning model our ultimate goal is to create value. In this post, the author illustrates how data visualization can be a powerful tool in choosing and understanding the modeling decisions that maximize business value.
- R vs Python: head to head data analysis
There have been dozens of articles written comparing Python and R from a subjective standpoint, but this DataQuest article aims to look at the languages more objectively, showing what code is needed in both languages to achieve the same result: analyzing a small data set.
- Unboxing the Random Forest Classifier: The Threshold Distributions
This Airbnb article describes a method to aggregate and summarize feature split values in a random forest by generating weighted threshold distributions, hence offering a method to succinctly describe how feature are being split.
- What to do with “small” data?
What to do in situations where you are dealing with small data sets?
- The wonderful world of recommender systems
This article discusses the different types of recommender systems, and what makes them wonderful.
- Data Science Project Checklist To Use Before You Start A Project To Convey You Can Actually Get Work Done
You’re about to start a data science project, and you’re looking to make sure that you’re going to be on the right track. This blog post presents a handy checklist of things to keep in mind.
- “Memory foam” approach to unsupervised learning
The authors of this paper propose an alternative approach to construct an artificial learning system, which naturally learns in an unsupervised manner. Its mathematical prototype is a dynamical system, which automatically shapes its vector field in response to the input signal.
- OpenFace: Face recognition with Google’s FaceNet deep neural network
This is a Python and Torch implementation of the CVPR 2015 paper FaceNet: A Unified Embedding for Face Recognition and Clustering by Florian Schroff, Dmitry Kalenichenko, and James Philbin at Google using publicly available libraries and datasets.
- Hacking the Random Walk Hypothesis
This article subjects various financial market returns to the NIST suite of tests to test the robustness of random number generators to see whether or not such market movements are in fact, equivalent to random walks.
- Auto-Generating Clickbait With Recurrent Neural Networks
Writers have become very good at squeezing out the maximum clickability out of every headline. What if we could automate the writing of these? This fun blog post aims to find out.
- Deep-Learning Robot Takes 10 Days to Teach Itself to Grasp
Leave a human baby with some toys and it’ll quickly learn to pick them up. Now a robot with deep-learning capabilities has done the same thing.
- Applications of Machine Learning in FinTech
Five applications of machine learning as used in the FinTech ecosystem.
- Five principles for applying data science for social good
This article outlines five principles that can aid the movement to use data and data science for good.
- Recurrent Neural Networks Tutorial, Part 3 – Backpropagation Through Time and Vanishing Gradients
Third part of the tutorial we saw appearing a while ago The author sets out the how the reader step-by-step how RNNs work, and how to implement them using Python and Theano.
- Deep learning – Convolutional neural networks and feature extraction with Python
Another article showing off the basic workings of convolutional neural networks in Python.
- Rodeo 1.0 released
yhat announces the release of their in-browser Python IDE.
- Julia 0.4 released
The Julia community announces the release of Julia version 0.4.0.
