Data Machina #144

I love fractals. I still remember the first time I generated a fractal. I really enjoyed reading My Journey into 3D Fractals.

I felt like I run a knowledge marathon ater attending Spark+AI Summit London You can watch all the 126 sessions here.

10 Link-o-Troned

1. A Guide to The Machine Learning Engineering Loop

2. Unveiling Mathematics behind XGBoost

3. Embeddings @Twitter

4. [perhaps] The 25 Best Data Visualizations of 2018

5. Open sourced: MS infer.NET Bayesian Inference Framework

6. Serverless Machine Learning with Tensorflow.js

7. Stanford Seminar - Computing with High-Dimensional Vectors

8. Introduction to Probabilistic Programming (pdf, 218 pages)

9. Online Experiments & Bayesian Optimization @Facebook

10. [early access ebook] Model-Based Machine Learning

A Pythonista *Experience*

1. skpro- A Prediction Framework for Probabilistic Modelling

2. MS Neural Intel Net: A Toolkit for Automated ML Experiments

3. fastai v1 PyTorch: Fast, Accurate, Modern NNs Best Practices

Scripting aRt

1.  Statistically Sound Data Preparation for Predictive Modeling

2. Databricks MLFlow with R

3. Boosting Smooth Trees for Pricing Optimization

Love from Julia

1. Turing.jl - A Universal Probabilistic Language in Julia

2. Introduction to Sparse Data & Word Embeddings

3. Nearest Neighbor Descent in Julia 

(Paren(th)ethical)

1. Clojure, Mental Focus & Machine Learning

2. Running with Scissors: Live Coding with Data

3. The MiniMax Algo in Clojure (using Reduce)

ScalaTOR

1. Just Enough Scala for Spark Programmers

2. fs2 - Functional Streams for Scala

3. VEGAS: The Missing Matplotlib for Scala Spark

data v-i-s-i-o-n-s

1.  A Python Library for Decision Tree Visualization

2. Visual Analysis & Comparison of London Property Market

3. A Map of Every Building in America

Distributed de-Entangler

1. Kubernetes for Personal Projects? No thanks!

2. Designing Events-First Microservices

3. Spark Streaming + Kafka: An Integration Story

Blockchain Über Alles

1. Is Proof-of-Work a Waste?

2. Blockchain is a Semantic Wasteland

3. MIT How Blockchain Works - A Visual Demo

IoTea - everyThing/anyThing

1. Whisper Detection in Alexa with a RNN-LSTM

2. An Upgrade Strategy for Embedded Linux Systems

3. ESP8266 Based Project for Securing Hotel Rooms

Forschung!

1. Probabilistic Tales: Discriminative, Descriptive & Generative

2. BERT: New, State-of-the-Art Language Representation Model

3. FashionNet: Personalized Outfit Recommendations with DNN

Algorithmic Potpourri

1. Wikipedia Web Crawler & PageRank Algorithm Implementation

2. Multi-Armed Bandit Implementation in Python

3. Advisor - Hyper Parameter Tuning for Black Box Optimisation

Robots & Cyborgs like <you>

1. Atlas Robot Does Parkour Like It’s Easy [we’re all going to die]

2. ros-win: Robotics Operating System (ROS) in Windows 10

3. What Happens When a Drone Hits an Airplane Wing?

Deep & Other Types of Learning Bits

1. Uber Petastorm: Open Source Data Access Lib for Deep NN

2. Practical Guide to Hyperparameters Search for Deep Learning

3. Hands-On Transfer Learning with Python

startups -> radar

1. Embod.ai - MMO Arcade Games for Artificial Intelligence

2. PlateRecognizer - Auto License Plate Recognition as a Service

3. Rapids.ai - Fast, Open GPU Data Science Pipelines

ML Datasets & Stuff

1. Standford Clothing Attributes Dataset for Computer Vision

2. Harvard Unicorn Intrusion Detection Dataset

3. The Optical Illusion Dataset

Postscript, etc

Spread the word Share Data Machina with your friends

Tips? Suggestions? Feedback? Send email to Carlos

Curated by Carlos @ds_ldn in the middle of the night.