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
(Paren(th)ethical)
1. Replephant: Analyzing Hadoop Cluster Usage with Clojure
2. Data Science Screencasts from Lambda Island
3. Rica - Data-frame Abstraction for Clojure Data Scientists
ScalaTOR
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
Forschung!
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