Data Machina #142

The amazing power of GANs and adversarial learning… Given a video of an expert dancer and another video of an amateur dancer, train the amateur video to dance like an expert… Everybody Dance Now - Watch the video and read the paper here

When confronted with a dull, long, bank holiday, you may find time to read Blindsight, the sci-fi novel where 5 transhumans set off on a journey riding the Theseus - a spaceship captained by an AI- in search for aliens (pdf, 340 pages)

10 Link-o-Troned

1. Bayesian Data Science: Simulation & Probabilistic Programming

2. NLP’s Generalization Problem: How Researchers are Tackling it

3. Serverless for Data Scientists

4. Learning Meaning in NLP- The Semantics Mega-Thread

5. Understanding What Artificial Intelligence Actually Sees

6. MMLSpark = Spark + MS CNTK + LightGBM + OpenCV

7. [new] Google’s Fast Prototyping Reinforcement Learning

8. Federated Machine Learning & Federated Optimization

9. How to Analyze Billions of Records per Second on a Single PC

10. What They Don’t Tell You About Event Sourcing

A Pythonista *Experience*

1. SparkFlow: Train Tensorflow Models with Spark Pipelines

2. DoWhy- a Python Library for Estimating Causal Effects

3. DeepMind’s Relational RNNs Implemented in PyTorch 

4. [course] Probabilistic Programmer Primer in Python

Scripting aRt

1. A Package for Logitudinal Analysis & Clustered Data Regression

2. Full Bayesian Inference for Hidden Markov Models

3. An LSTM that Writes R Code

Love from Julia

1. Reinforcement Learning & Generative Models Using Flux

2. Speech Recognition for the Flux Machine Learning Model Zoo

3. Monte-Carlo Optimization in Julia

(Paren(th)ethical)

1. Example Projects for NLP and ML in Clojure

2. Clojure Advanced Regression & ML for Kaggle House Prices

3. Clojure Sandbox for Streaming Data Platforms

ScalaTOR

1. ScalphaGoZero - DeepMind’s AlphaGoZero in Scala

2. Streaming Data from PostgreSQL with Akka Streams

3. Tencent’s Distributed, Parameter Server for Large-Scale ML

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

1. ccNetViz - A Library for Large Graph Network Dataviz

2. Interactive Self-Organizing Map (SOM) Visualization

3. Visualize the First 1 Million Integers in the 2D Space w/ UMAP

Distributed de-Entangler

1. Serverless Best Practices

2. Apache Storm Key Takeaways

3. Notebooks at Scale: Zero to JupyterHub with Kubernetes

Blockchain Über Alles

1. Decentralized Websites on the IPFS (Interplanetary Filesystem)

2. Atomic Swaps Intro: No Middleman,Crypto Trades in Any Chain

3. The Authoritative Guide to Blockchain Development

IoTea - everyThing/anyThing

1.  How We Do IoT Edge Computing at Chick-fil-A

2. Fully Private, Open-Source Home Automation on Raspberry Pi

3. An Intro to Time Series Insights for IoT on Azure

Forschung!

1. Training Classifiers with Natural Language Explanations

2. Benchmarking Automatic Machine Learning Frameworks

3. UMAP - Novel Manifold Learning for Dimensionality Reduction

Algorithmic Potpourri

1. A Practical Intro to the Min-Count Sketch

2. The PCSA-TC Algo for Probabilistic Counting in Data Streams

3. An Assortment of Genetics Algorithms in Python

Robots & Cyborgs like <you>

1. Deep Learning & Humanoids for Autism Therapy

2. How Robot Hands Are Evolving to Do What Ours Can

3. The AI Self-Driving Olympics

Deep & Other Learning Bits

1. DeepChef: Get Dish Cooking Recipe from the Photo of the Dish

2. The Stanford’s Deep Learning Cheatsheets

3. [project] Reinforcement Learning for Self-Balancing Motorbike

startups -> radar

1. DataBrockerDao - Blockchain-based Market for IoT Sensor Data

2. Lang.ai -Unsupervised AI Platform for Language Understanding

3. Galaxy.ai - AI for Automated Insurance Claims

ML Datasets & Stuff

1. FEVer-Large-scale Fact Extraction & Verification, 185K Facts

2. QuAC - Question & Answering in Context Dataset

3. IAM Handwriting 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.