Receive the Data Science Weekly Newsletter every Thursday

Easy to unsubscribe at any time. Your e-mail address is safe.

Data Science Weekly Newsletter
November 1, 2018

Editor's Picks

  • Is a straight line the shortest path?
    Is the shortest path from to the straight line between them? Your first response might be to think it's obviously so. But in fact you know that it's not quite that straightforward...
  • Reinforcement Learning with Prediction-Based Rewards
    We’ve developed Random Network Distillation (RND), a prediction-based method for encouraging reinforcement learning agents to explore their environments through curiosity, which for the first time1 exceeds average human performance on Montezuma’s Revenge. RND achieves state-of-the-art performance, periodically finds all 24 rooms and solves the first level without using demonstrations or having access to the underlying state of the game...
  • Deep Dreaming with Deep Learning
    Can a machine dream? Yes, it can. A machine dreams or hallucinates by mimicking low-level visual systems of the human brain, in order to perceive patterns and categorise objects. The machine begins to produce outputs even in the absence of any inputs...

A Message From This Week's Sponsor

Learn data science now, pay after you get a job.

If you’re looking for more advanced learning in data science, check out Springboard’s Data Science Career Track
. With one-on-one mentorship and career support, the Data Science Career Track is designed to help you master job-ready skills and actually land your dream job. To make the Career Track more accessible, Springboard now has a new payment plan: deferred tuition.
With Springboard's Deferred Tuition Plan
, you can enroll in the Data Science Career Track for a small upfront deposit, with no additional payment until you complete the course and start a new job! If you stick to the plan, but don’t find a job, the course is free.
Apply today!

Data Science Articles & Videos

  • Humans are still the best lossy image compressors
    Lossy image compression has been studied extensively in the context of typical loss functions such as RMSE, MS-SSIM, etc. However, it is not well understood what loss function might be most appropriate for human perception. Furthermore, the availability of massive public image datasets appears to have hardly been exploited in image compression. In this work, we perform compression experiments in which one human describes images to another, using publicly available images and text instructions...
  • Introducing AdaNet:
    Fast and Flexible AutoML with Learning Guarantees

    Today, we’re excited to share AdaNet, a lightweight TensorFlow-based framework for automatically learning high-quality models with minimal expert intervention. AdaNet builds on our recent reinforcement learning and evolutionary-based AutoML efforts to be fast and flexible while providing learning guarantees. Importantly, AdaNet provides a general framework for not only learning a neural network architecture, but also for learning to ensemble to obtain even better models...
  • How to Decide Which Data Science Projects to Pursue
    In 2018, every organization has a data strategy. But what makes a great one? We all know what failure looks like. Resources are invested, teams are formed, time goes by — but nothing comes of it. No one can necessarily say why; it’s always Someone Else’s Fault. It’s harder to tell the difference between a modest success and excellence. Indeed, in data science they can they look very similar for perhaps a year. After several years, though, an excellent strategy will yield orders of magnitude more valuable results...
  • How to Engineer Your Way Out of Slow Models
    In this post I describe how we at Taboola handle performance issues with some of our deep learning models: We find subgraphs that take a lot of calculation time. We extract these subgraphs into a caching mechanism. At train/inference time we query the cache to get instant outputs of these subgraphs. Cache miss? Send a request to another service that will run inference on the subgraphs...


  • Senior Data Scientist/Machine Learning Engineer - PepsiCo eCommerce - NYC

    Want to build an RL system with real money against business experts? Apply now!
    PepsiCo operates in an environment undergoing immense and rapid change, driven by eCommerce and emergent retail technologies. To ensure continued success in the food and beverage space, PepsiCo has assembled a dedicated eCommerce team – tasked with optimizing eCommerce operations and developing innovations that will give PepsiCo a sustainable competitive advantage. While tied closely to broader PepsiCo, the eCommerce group more closely resembles a start-up environment; embracing the core values of having bias for action, being results oriented, maintaining a community-focus, and prioritizing people.
    PepsiCo’s Data Science and Analytics group is a team of data scientists, technology specialists, and business innovators who operate within eCommerce to build industry-leading systems and solutions. By focusing on machine learning and automation, the Data Science & Analytics group is pushing the bounds of possibility for PepsiCo and its strategic partners...

Training & Resources

  • Create TensorFlow Name Scopes For TensorBoard
    Learn how to use TensorFlow Name Scopes (tf.name_scope) to group graph nodes in the TensorBoard web service so that your graph visualization is legible, via a screencast video and full tutorial transcript...
  • sklearn-porter
    Transpile trained scikit-learn estimators to C, Java, JavaScript and others. It's recommended for limited embedded systems and critical applications where performance matters most...


  • Data Smart: Using Data Science to Transform Information into Insight
    "The best single book on Data Science today. I handle the data analysis and BI for the delivery side of a huge internet-based retail company, and have been a fan of Foreman's since his "Analytics Made Skeezy" blog days. His explanations are clear, his examples are to the point, and throughout it all, he is results-oriented."...

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

Easy to unsubscribe at any time. Your e-mail address is safe.