Data Science Weekly - Issue 230
Issue #230 Apr 19 2018
Editor Picks
How I Taught A Machine To Take My Job
or Behavioral Cloning and 3D Procedural Content Generation
I recently discussed how we could use convolutional neural networks for gesture recognition in VR. I concluded that while it was really cool, drawing objects was sometimes more tedious that having a simple menu. So that got me thinking… What if I used neural networks to anticipate what objects I wanted to place?...
Decades-Old Graph Problem Yields to Amateur Mathematician
By making the first progress on the “chromatic number of the plane” problem in over 60 years, an anti-aging pundit has achieved mathematical immortality...
Canning the can’t — fun with homonyms and word vectors
As a company specialised in natural language understanding, word embeddings are one of the building blocks of our technology. Our NLU models need to be capable of correctly ‘understanding’ what is written or said...
A Message from this week's Sponsor:
Quick Question For You: Do you want a Data Science job?
After helping hundred of readers like you get Data Science jobs, we've distilled all the real-world-tested advice into a self-directed course.
The course is broken down into three guides:
Data Science Getting Started Guide. This guide shows you how to figure out the knowledge gaps that MUST be closed in order for you to become a data scientist quickly and effectively (as well as the ones you can ignore)
Data Science Project Portfolio Guide. This guide teaches you how to start, structure, and develop your data science portfolio with the right goals and direction so that you are a hiring manager's dream candidate
Data Science Resume Guide. This guide shows how to make your resume promote your best parts, what to leave out, how to tailor it to each job you want, as well as how to make your cover letter so good it can't be ignored!
Data Science Articles & Videos
Who's a Good AI? Dog-based data creates a canine machine learning system
We’ve trained machine learning systems to identify objects, navigate streets and recognize facial expressions, but as difficult as they may be, they don’t even touch the level of sophistication required to simulate, for example, a dog. Well, this project aims to do just that — in a very limited way, of course...
Hallucinogenic Deep Reinforcement Learning Using Python and Keras
Teaching a machine to master car racing and fireball avoidance through “World Models”...
Forecasting Uber Demand in NYC
I decided to see if I could forecast hourly Uber demand across NYC neighborhoods. In addition to time-lagged features (such as previous week’s demand), I added information specific to each neighborhood to improve my predictions. As a final result, I obtained relatively accurate unique forecasts for all neighborhoods in NYC...
Paper Repro: Deep Neuroevolution
In this post, we reproduce the recent Uber paper “Deep Neuroevolution: Genetic Algorithms are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning”, which amazingly showed that simple genetic algorithms sometimes performed better than apparently advanced reinforcement learning algorithms on well studied problems such as Atari games. We will ourselves reach state of the art performance on Frostbite)...
Text Embedding Models Contain Bias. Here's Why That Matters.
Neural network models can be quite powerful, effectively helping to identify patterns and uncover structure in a variety of different tasks, from language translation to pathology to playing games. At the same time, neural models (as well as other kinds of machine learning models) can contain problematic biases in many forms...
Imagine This! Scripts to Compositions to Videos
Researchers trained an AI to create Flintstones cartoons...
Probabilistic Machine Learning in TensorFlow
In this episode of Coffee with a Googler, Laurence Moroney sits down with Josh Dillon. Josh works on TensorFlow, Google’s open source library for numerical computation, which is typically used in Machine Learning and AI applications. He discusses working on the Distribution API, which is based on probabilistic programming. Watch this video to find out what exactly probabilistic programming is, where the use of Distributions and Bijectors comes into play, & how you can get started...
Ads That Click
Classifying Ads using CATBoost Model based on the features of the ads and the user’s behavior. The objective of my project was to analyze user behavior and derive if they will like a particular ad in the future or not. The intent was to maximize the value of the advertiser at the same time improve the user experience...
Jobs
Data Scientist - VillageCare - NYC
VillageCare is a community-based, non-profit organization serving people with chronic care needs, as well as seniors and individuals in need of continuing care and rehabilitation services.
The Data Scientist will support our Provider Relations team with insights gained from analyzing company data. The ideal candidate is adept at using large data sets to find opportunities for product and process optimization and using models to test the effectiveness of different courses of action...
Training & Resources
Specify PyTorch Tensor Minimum Value Threshold
Learn how to specify PyTorch Tensor Minimum Value Threshold by using the PyTorch clamp operation, via a screencast video and full tutorial transcript...
Speech Processing for Machine Learning: Filter banks, Mel-Frequency Cepstral Coefficients (MFCCs) and What's In-Between
In this post, I will discuss filter banks and MFCCs and why are filter banks becoming increasingly popular...
mltest: Automatically test neural network models in one function call
With incredibly little setup, we now are testing against several different common machine learning issues...
Books
Data Science from Scratch: First Principles with Python "It does three things superbly: covers the basic low level tools of a data scientist (the "from scratch" part), gives a great overview of useful Python programming examples for those new to Python, and gives an amazingly succinct yet high level overview of the mathematics and statistics required for data science..."
For a detailed list of books covering Data Science, Machine Learning, AI and associated programming languages check out our resources page.
P.S., Want to reach our audience / fellow readers? Consider sponsoring - grab a spot now; first come first served! All the best, Hannah & Sebastian