Data Science Weekly Newsletter - Issue 169

Issue #169

Feb 16 2017

Editor Picks
 
  • Were there more notable deaths than expected in 2016?
    After exploring my study population of Wikipedia deaths, I want to analyse the time series of monthly counts of notable deaths. This is not a random interest of mine, my PhD thesis was about monitoring time series of count, the application being weekly number of reported cases of various diseases...
  • Building a deep learning DOOM bot
    This article is the first in a series of posts that will focus on an exploratory journey of reinforcement based Deep Learning utilizing the VizDoom platform. In terms of goals, my destination is the creation of a Doom AI capable of thriving in a Deathmatch environment (woohoo killer AI)...
 
 

A Message from this week's Sponsor:

 

 
 

Data Science Articles & Videos

 
  • Neural Network Learns to Select Potential Anticancer Drugs
    Scientists from Mail.Ru Group, Insilico Medicine and MIPT have for the first time applied a generative neural network to create new pharmaceutical medicines with the desired characteristics. By using Generative Adversarial Networks (GANs) developed and trained to "invent" new molecular structures, there may soon be a dramatic reduction in the time and cost of searching for substances with potential medicinal properties...
  • Music Composition with LSTMs
    For my final project at Metis Data Science, I designed a recurrent neural network utilizing Long Short-Term Memory nodes (LSTMs) to learn patterns in the Six Cello Suites by J.S. Bach, and subsequently generate its own musical fragments...
  • Trump2Cash
    This bot watches Donald Trump's tweets and waits for him to mention any publicly traded companies. When he does, it uses sentiment analysis to determine whether his opinions are positive or negative toward those companies. The bot then automatically executes trades on the relevant stocks according to the expected market reaction. It also tweets out a summary of its findings in real time...
  • Data Selfie
    A new Chrome extension reveals the unsettling amount of information Facebook might have on you...
  • Fueling the Gold Rush: The Greatest Public Datasets for AI
    Most people in AI forget that the hardest part of building a new AI solution or product is not the AI or algorithms — it’s the data collection and labeling. Standard datasets can be used as validation or a good starting point for building a more tailored solution...
  • Duplicate Question Detection with Deep Learning on Quora Dataset
    Quora recently announced the first public dataset that they ever released. It includes 404351 question pairs with a label column indicating if they are duplicate or not. In this post, I like to investigate this dataset and at least propose a baseline method with deep learning...
 
 

Jobs

 
  • Data Scientist - SeatGeek - NYC

    SeatGeek operates a unique business model in a complicated, opaque market. Many of the hardest problems we face have never been tackled at scale and do not have clear questions, let alone answers. Moving forward requires critical thinking, rapid prototyping, and intellectual dexterity...
 
 

Training & Resources

 
  • R for Excel Users
    Excel users have a strong mental model of how data analysis works, and this makes learning to program more difficult. However, learning to program will allow you to do things that you can't do easily in Excel, and it really is worth the pain of learning the new model...
 
 

Books

 

 
 
P.S. Interested in reaching fellow readers of this newsletter? Consider sponsoring! Email us for details :) - All the best, Hannah & Sebastian
 
Sign up to receive the Data Science Weekly Newsletter every Thursday

Easy to unsubscribe. No spam — we keep your email safe and do not share it.