Data Science Weekly Newsletter - Issue 308

Issue #308

Oct 17 2019

Editor Picks
 
  • Solving Rubik’s Cube with a Robot Hand
    We’ve trained a pair of neural networks to solve the Rubik’s Cube with a human-like robot hand. The neural networks are trained entirely in simulation, using the same reinforcement learning code as OpenAI Five paired with a new technique called Automatic Domain Randomization (ADR). The system can handle situations it never saw during training, such as being prodded by a stuffed giraffe. This shows that reinforcement learning isn’t just a tool for virtual tasks, but can solve physical-world problems requiring unprecedented dexterity...
  • The State of Machine Learning Frameworks in 2019
    My analysis suggests that researchers are abandoning TensorFlow and flocking to PyTorch in droves. Meanwhile in industry, Tensorflow is currently the platform of choice, but that may not be true for long...
 
 

A Message from this week's Sponsor:

 

 
SQL, Python, and R. All in One Platform. Free Forever

Mode Studio combines a SQL editor, Python & R notebooks, and visualization builder in one platform. Connect data from anywhere and analyze with your preferred language. Layer custom visualizations (HTML, CSS, or D3.js) or use out-of-the-box charts.

Sign Up - Free Forever

 
 

Data Science Articles & Videos

 
  • Football Commentaries for The Visually Impaired
    Someone in Columbia created a way of communicating a football match situation for his blind friend on a small football board. However, this is only one person, what about so many others? How can we scale help up? You may think that translating traditional commentaries. However, these commentaries tend to focus on the players. I want to explain the general situation in a match, using deep learning and computer vision...
  • Clustering NBA Playstyles Using Machine Learning
    I love basketball. I love playing it, watching it, or arguing scenarios with friends like who would win one on one, Kobe or Lebron. I had to combine my two passions, basketball and data science, in a machine learning project...
  • On Empirical Comparisons of Optimizers for Deep Learning
    Selecting an optimizer is a central step in the contemporary deep learning pipeline. In this paper, we demonstrate the sensitivity of optimizer comparisons to the metaparameter tuning protocol. Our findings suggest that the metaparameter search space may be the single most important factor explaining the rankings obtained by recent empirical comparisons in the literature. In fact, we show that these results can be contradicted when metaparameter search spaces are changed. As tuning effort grows without bound, more general optimizers should never underperform the ones they can approximate...
  • Sis: Simple Image Search Engine
    Sis is a simple image-based image search engine using Keras + Flask. You can launch the search engine just by running two python scripts...
  • Conversational Sentiment Analysis
    As it turns out, using text to determine whether someone likes vs dislikes a movie, or any named entity, is deceivingly complex. This is especially true in conversational settings where structure is freeform and few assumptions can be made. Comparing a conversational setting to that of product reviews can help to illustrate the point...
  • Stabilizing Transformers for Reinforcement Learning
    Finally, Transformers working for RL! Two simple modifications: move layer-norm and add gating creates GTrXL: an incredibly stable and effective architecture for integrating experience through time in RL...
  • exBERT: A Visual Analysis Tool to Explore Learned Representations in Transformers Models
    We present exBERT , an interactive tool named after the popular BERT language model, that provides insights into the meaning of the contextual representations by matching a human-specified input to similar contexts in a large annotated dataset. By aggregating the annotations of the matching similar contexts, exBERT helps intuitively explain what each attention-head has learned...

 

Training*

 

 
Create D3 Data Visualizations As Fast As You Can Sketch

You need to create a D3.js data visualization to communicate your insights. But... #d3BrokeAndMadeArt! This time, your data join appears to have broken and the JavaScript console shows an error you don't recognize. Last time, you got stuck trying to figure out how to make axes that didn't look like 3rd graded made them. It makes you want to strangle D3 with your bare hands. Just how steep does the D3 learning curve need to be?!

What if you could learn and master D3 quickly and deeply?

Great news! - You can ... Check out DashingD3js.com Screencasts today!

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

 

 

Jobs

 
  • Developer Advocate: NLP - Rasa -
    San Francisco / Remote US or Berlin, Germany


    Developer Advocates are extremely important for the success of open source projects and we are looking for new team members to help us grow our open source community. At Rasa, it’s an exciting mix of working on bleeding-edge machine learning projects, hacking with new technologies, speaking at developer conferences all around the world and educating devs about ML, conversational AI, and our tools.

    What do you need to become a developer advocate? Two things: a passion for ML and an eagerness to teach and help others. If this sounds like you, then send your application to L.morley@rasa.com...

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

 

Training & Resources

  • Neural Structured Learning: Training with Structured Signals
    Neural Structured Learning (NSL) is a new learning paradigm to train neural networks by leveraging structured signals in addition to feature inputs. Structure can be explicit as represented by a graph or implicit as induced by adversarial perturbation...
  • 5 Significant Object Detection Challenges and Solutions
    Object detection problems pose several unique obstacles beyond what is required for image classification. Five such challenges are reviewed in this post along with researchers' efforts to overcome these complications...

 

Books

 

  • The Lady Tasting Tea:
    How Statistics Revolutionized Science in the Twentieth Century

    An insightful, revealing history of how mathematics transformed our world...

    "I have taken courses in statistics, taught it many times and solved several statistical problems that have appeared in journals. But until I read this book, I never really thought about it in so deep and philosophical a manner..."


    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.