Data Machina #143

This is really cool: The GAN Lab: Play with Generative Adversarial Networks (GANs) in Your Browser

There’s a lot! going on in Open Source Modern Data Engineering. Check out: Facebook’s LogDevice: A Distributed, High-availability Storage for Sequential Data and Uber’s Marmaray: A Scalable, Data Ingestion Framework for Any Source, Any Sink

This is a fascinating read: The Man Who Won The Lottery 14 Times

10 Link-o-Troned

1. Time-Series Prediction Using RNN-LSTM

2. Forecasting @Uber: An Introduction

3. Machine Learning, Information Theory & Tail Bounds

4. The Use of Embeddings in OpenAI Five

5. AVA Algorithms: The Art & Science of Image Discovery @Netflix

6. Multi-Armed Bandits and Bayesian Reinforcement Learning

7. Prediction Markets: When Do They Work?

8. Variational Autoencoders Explained

9. What-If-Tool: Inspect Machine Learning Models with No Code

10. A Personal Essay on Bayes Factors

A Pythonista *Experience*

1. Mantra - Rapid Dev Framework for Machine Learning Projects

2. fastTSNE - A Fast, Parallel, Python Implementation of tSNE

3. Gensim Tutorial : File-based Fast Training for Any2Vec Models

Scripting aRt

1. Forecasting Thunderstorms with Generalized Additive Models

2. Training, Evaluating and Interpreting Topic Models

3. FeatureImp: Compute Feature Importance in Prediction Models

Love from Julia

1. Julia for Probabilistic Metaprogramming

2. The Julia Language Challenge

3. PredictMD - Uniform Interface for Machine Learning in Julia


1. Replephant: Analyzing Hadoop Cluster Usage with Clojure

2. Data Science Screencasts from Lambda Island

3. Rica - Data-frame Abstraction for Clojure Data Scientists


1. Bank Marketing Campaign Machine Language Model in Scala

2. Scala Machine Learning Projects: Recommendation Systems

3.  Random Data Generation with Scalacheck

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

1. Deep Learning Based Visualization of Hurricane Intensity

2. Simple Diagrams for Convoluted Neural Networks

3. Interactive Dataviz: London Atmospheric Emissions by Street

Distributed de-Entangler

1. Tensorflow in Docker on Kubernetes - Read This First

2. Putting the Power of Kafka in the Hands of Data Scientists

3. Keystone: Real-time Streaming w/ Kafka & Flink @Netflix

Blockchain Über Alles

1. The Whole Ethereum Blockchain Data in Google BigQuery

2. Overview and Intro to Tokenized Securities

3. Elements Project: Advanced Blockchain, Extending Bitcoin

IoTea - everyThing/anyThing

1. What I Learned Making 5 ARKit Augmented Reality Prototypes

2. Low.js, the Port of Node.js for Embedded Devices

3. MainFlux Opensource, Industrial IoT Messaging & Device Mgmt


1. Propheticus: Generalizable Machine Learning Framework

2. Hypergraph CNNs for Semi-Supervised Classification

3. Machine Learning & Cryptography Against Adversarial Attacks

Algorithmic Potpourri

1. Machine Learning and Flocking Algorithms in Swarm Drones

2. Damn Cool Algorithms: Levenshtein Automata

3. Simple, Real-Time Obstacle Avoidance Algos for Mobile Robots

Robots & Cyborgs like <you>

1. The OpenDog Project: Opensource Robotic Dog

2. The Unity Machine Learning Agents Kit

3. DelFly- A Flapping Wing Robot that Flies Like an Insect

Deep & Other Learning Bits

1. DeepStack - Expert Level AI in Heads-up, No-Limits Pocker

2. Yann LeCun - Deep Learning, Structure and Innate Priors

3. A (Long) Peek into Reinforcement Learning

startups -> radar

1. Bloom - Leading Edge Robotics for the Cannabis Industry

2. Atrium - Replacing Lawyers with Machine Learning

3. Intiva- Hashgraphs for Instant Medical Credentials Verification

ML Datasets & Stuff

1. 28 Years of Hubble Space Telescope Imagery on AWS

2. Opin Rank Dataset - 300K Cars and Hotels Reviews

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.

3. NuScenes, a Self-driving Dataset with +1.4 Million Images