Here’s our weekly roundup of articles published this week about Machine Learning and Data Science. Hope you find it useful – please don’t forget to subscribe!
- Artificial Intelligence vs Machine Learning vs Deep Learning
This is the first of a multi-part series explaining the fundamentals of deep learning by long-time tech journalist Michael Copeland.
- Selecting a right Machine Learning algorithm for predictive analytics needs: Classification vs Regression vs Clustering
An interesting cheat sheet was published by Microsoft sometime back to help beginning data scientists on how to choose a Machine Learning algorithm for different predictive analytics needs: Classification (to predict categories), Clustering (to discover structure), Regression (to predict values) and Anomaly Detection (to find unusual data points).
- Dask and scikit-learn: a 3-Part Tutorial
Dask core contributor Jim Crist has put together a series of posts discussing some recent experiments combining Dask and scikit-learn on his blog. The tutorial spans three posts, which covers model parallelism, data parallelism and combining the two with a real-life dataset.
- From Dev to Ops: Building a Text Classifier using Python and Docker — Part 1: Docker
Matt von Rohr shows how to build a text classification algorithm using Docker, Python, Jupyter Notebook, Scikit-learn and Flask to classify news articles.
- Face Recognition with Deep Learning + Demo (Python, OpenFace and dlib)
Adam Geitgey describes how modern face recognition works, and shows how one can build a facial recognition system using Python, OpenFace (a Python and Torch implementation of face recognition with deep neural networks) and dlib (a toolkit for making real world machine learning and data analysis applications in C++).
- Neural Networks: What Are They, And Why Is The Tech Industry Obsessed With Them?
From Deep Dream to Deep Drumpf, everyone’s talking about neural networks these days. But what the heck are neural networks and what do they mean for the future of computing and design? Here’s your quick primer.
- Image recognition in R using convolutional neural networks with the MXNet package
- Great R packages for data import, wrangling & visualization
Sharon from Computerworld writes about her favorite R packages for data visualization and munging. She also mentions a few important tips for R newbies like: how to install a R package from CRAN and github.
- A Neural Network Scoring Engine in PL/SQL
Luca Canali shows how to build and deploy a simple neural network scoring engine to recognize handwritten digits using Oracle and PL/SQL. The final result is a short PL/SQL package with an accuracy of about 98%. The neural network is built and trained using TensorFlow and then transferred to Oracle for serving it.
- The 9 Best Languages For Crunching Data
Here’s a roadmap to the latest and greatest tools in data science – R, Python, Julia, Java, Hadoop and Hive, Scala, Kafka and Storm, Matlab, Octave & Go – and when one should use them.