Data Science Weekly Newsletter - Issue 388

Issue #356

Sep 17 2020

Editor Picks
 
  • ICML 2020 Videos + Slides
    The International Conference on Machine Learning (ICML) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence known as machine learning...ICML is one of the fastest growing artificial intelligence conferences in the world. Participants at ICML span a wide range of backgrounds, from academic and industrial researchers, to entrepreneurs and engineers, to graduate students and postdocs...
  • Array programming with NumPy
    Here we review how a few fundamental array concepts lead to a simple and powerful programming paradigm for organizing, exploring and analysing scientific data. NumPy is the foundation upon which the scientific Python ecosystem is constructed. It is so pervasive that several projects, targeting audiences with specialized needs, have developed their own NumPy-like interfaces and array objects. Owing to its central position in the ecosystem, NumPy increasingly acts as an interoperability layer between such array computation libraries and, together with its application programming interface (API), provides a flexible framework to support the next decade of scientific and industrial analysis...
  • Transformers are Graph Neural Networks
    My engineering friends often ask me: deep learning on graphs sounds great, but are there any real applications?...While Graph Neural Networks are used in recommendation systems at Pinterest, Alibaba and Twitter, a more subtle success story is the Transformer architecture, which has taken the NLP world by storm. Through this post, I want to establish a link between Graph Neural Networks (GNNs) and Transformers. I'll talk about the intuitions behind model architectures in the NLP and GNN communities, make connections using equations and figures, and discuss how we can work together to drive future progress. Let's start by talking about the purpose of model architectures—representation learning...
 
 

A Message from this week's Sponsor:

 

 
Data scientists are in demand on Vettery

Vettery is an online hiring marketplace that's changing the way people hire and get hired. Ready for a bold career move? Make a free profile, name your salary, and connect with hiring managers from top employers today.
 
 
 

Data Science Articles & Videos

 
  • Apache Arrow: The Hidden Champion of Data Analytics
    In today’s open-source software stack you can find many indispensable dependencies in the form of software libraries. They are logging frameworks, testing frameworks, HTTP libraries, or code style checkers. But it doesn’t happen often that a new library emerges which changes the way we think about computing. One of such libraries in the data processing and data science space is Apache Arrow...It provides the following functionality: a) In-memory computing, b) A standardized columnar storage format, and c) An IPC and RPC framework for data exchange between processes and nodes respectively...Why is this such a big deal?...
  • Ensemble Networks
    Ensemble nets are a method of representing an ensemble of models as one single logical model. We use jax's vmap operation to batch over not just the inputs but additionally sets of model parameters. we propose some approaches for training ensemble nets and introduce logit dropout as a way to improve ensemble generalisation as well as provide a method of calculating model confidence...
  • The Generative Age
    AI can already create photorealistic faces, objects, and landscapes. Video isn’t far behind. We can already recreate any voice. GPT-3 can already write dialogue and movie plots almost indistinguishable from ones written by humans. Even generated music is making fast progress...It’s only a matter of time until we’re generating entire movies and shows. It’s startling to realize that Hollywood movies that cost $300M to produce today might be generated for a few cents within our lifetimes...When the cost of something drops by a factor of a billion we should expect to see qualitatively different uses...
  • How To Trick A Neural Network
    Neural networks get a bad reputation for being black boxes. And while it certainly takes creativity to understand their decision making, they are really not as opaque as people would have you believe...In this tutorial, I’ll show you how to use backpropagation to change the input as to classify it as whatever you would like...
  • DeepSpeed: Extreme-scale model training for everyone
    DeepSpeed is a deep learning optimization library that makes distributed training easy, efficient, and effective...10x Larger Models...10x Faster Training...Minimal Code Change...DeepSpeed delivers extreme-scale model training for everyone, from data scientists training on massive supercomputers to those training on low-end clusters or even on a single GPU...
  • Efficient Transformers: A Survey
    Transformer model architectures have garnered immense interest lately due to their effectiveness across a range of domains like language, vision and reinforcement learning...Recently, a dizzying number of "X-former" models have been proposed - Reformer, Linformer, Performer, Longformer, to name a few - which improve upon the original Transformer architecture, many of which make improvements around computational and memory efficiency. With the aim of helping the avid researcher navigate this flurry, this paper characterizes a large and thoughtful selection of recent efficiency-flavored "X-former" models, providing an organized and comprehensive overview of existing work and models across multiple domains...
  • Perceptron in COBOL
    A perceptron written in COBOL...I've been reading a lot about companies seeking COBOL programmers, so I decided to give it a shot and wrote a perceptron to classify the Iris dataset...
  • Multi-Armed Bandits and the Stitch Fix Experimentation Platform
    Multi-armed bandits have become a popular alternative to traditional A/B testing for online experimentation at Stitch Fix. We’ve recently decided to extend our experimentation platform to include multi-armed bandits as a first-class feature. This post gives an overview of our experimentation platform architecture, explains some of the theory behind multi-armed bandits, and finally shows how we incorporate them into our platform...
 
 

Training*

 

 
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:
  1. 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)

  2. 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

  3. 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!
Click here to learn more ...

*Sponsored post. If you want to be featured here, or as our main sponsor, contact us!
 

 

Jobs

 
  • Data Scientist - JetBlue - Long Island, NY

    The Data Scientist applies machine learning and statistical techniques to help solve JetBlue’s most complex commercial and operational challenges. The Data Scientist will be responsible for exploring and creating compelling visualizations of new datasets, identify key features and engineer new ones to be used in modeling, and discover the modeling approaches that deliver the best results based on appropriate evaluation metrics...

        Want to post a job here? Email us for details >> team@datascienceweekly.org
 

 

Training & Resources

 
  • high-fidelity-generative-compression
    This repository defines a model for learnable image compression based on the paper "High-Fidelity Generative Image Compression" (HIFIC) by Mentzer et. al.. The model is capable of compressing images of arbitrary spatial dimension and resolution up to two orders of magnitude in size, while maintaining perceptually similar reconstructions. Outputs tend to be more visually pleasing than standard image codecs operating at higher bitrates...This repository also includes a partial port of the Tensorflow Compression library - which provides general tools for neural image compression in Pytorch...
  • Deploy Machine Learning Models with Django
    This tutorial provides code examples on how to build your ML system available with REST API. In this book, for building the ML service I will use Python 3.6 and Django 2.2.4. This book is the first part that covers the basics which should be enough to build your ML system which: a) can handle many API endpoints, b) each API endpoint can have several ML algorithms with different versions, c) ML code and artifacts (files with ML parameters) are stored in the code repository (git), d) supports fast deployments and continuous integration (tests for both: server and ML code), e) supports monitoring and algorithm diagnostic (support A/B tests), f) is scalable (deployed with containers), g) and has a user interface...
  • The Sorcerer’s Apprentice Guide to Training LSTMs
    Tricks of the trade for training Long Short-Term Memory networks... Last year, I took a course at the Johannes Kepler University in Linz, Austria on the topic of Recurrent Neural Networks and Long Short-Term Memory Networks. There, Sepp Hochreiter shared some of the “magic tricks” he and his team employ for training LSTMs. This blog post is the accumulation of some of my notes...
 
 

Books

 

  • Hands-On Machine Learning with scikit-learn and Scientific Python Toolkits


    Integrate scikit-learn with various tools such as NumPy, pandas, imbalanced-learn, and scikit-surprise and use it to solve real-world machine learning problems...

    For a detailed list of books covering Data Science, Machine Learning, AI and associated programming languages check out our resources page.
     


    P.S., Enjoy the newsletter? Please forward it to your friends and colleagues - we'd love to have them onboard :) 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.