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.
- The Data Science Workflow
The folks from BinaryEdge reflect on the data science workflow, including steps regarding preliminary analysis, storytelling, and knowledge discovery.
- Deepdreaming without the Slugdogs
“In our deepnightmares, we’ve seen monstrous slugdogs, shoggoths of endless eyes, creatures beyond all reckoning.” Hence, the author presents some neural network “deep dreams” which were trained on datasets containing less animals.
- Introduction to Monte Carlo Tree Search
Jeff Bradberry describes how you can implement a Monte Carlo based Tree Search algorithm in Python, and why it’s better compared to Minimax.
- Jupyter and conda for R
Continuum Analytics is continuing to work on their support for the R ecosystem. The Anaconda team has now created an “R Essentials” bundle with the IRKernel and over 80 of the most used R packages for data science, so you can get started right away.
- Better interactive data science with Beaker and Rodeo
Domino announces support for Beaker notebooks (think: Jupyter notebooks on steroids and mixed-language support) and Rodeo (think: RStudio for Python).
- DataQuest’s Introduction to Spark
Learn Spark online using DataQuest’s interactive course.
- Deep Style: Inferring the Unknown to Predict the Future of Fashion
The engineers at Stitch Fix show how autoencoders can create new fashion style, starting from existing images.
- The Unreasonable Effectiveness of Random Forests
Among all the neural network hype, people are still discovering why random forests are so great.
- Giraffe: Using Deep Reinforcement Learning to Play Chess
This report presents Giraffe, a chess engine that uses self-play to discover all its domain-specific knowledge. Giraffe’s learning system also performs automatic feature extraction and pattern recognition.
- Recurrent Neural Networks Tutorial, Part 1 – Introduction to RNNs
The author sets out the how the reader step-by-step how RNNs work, and how to implement them using Python and Theano. (See also Implementing a Neural Network from Scratch in Python and Speeding up your Neural Network with Theano and the GPU from the same authors.)
