Data Science Weekly Newsletter - Issue 276

Issue #276

Mar 7 2019

Editor Picks
 
  • Launching TensorFlow Lite for Microcontrollers
    I’ve been spending a lot of my time over the last year working on getting machine learning running on microcontrollers, and so it was great to finally start talking about it in public for the first time today...
 
 

A Message from this week's Sponsor:

 

 
Find A Data Science Job Through Vettery

Vettery specializes in tech roles and is completely free for job seekers. Interested? Submit your profile, and if accepted onto the platform, you can receive interview requests directly from top companies growing their data science teams.

Get started.
 
 
 

Data Science Articles & Videos

 
  • The A.I. Diet: Forget government-issued food pyramids.
    Let an algorithm tell you how to eat.

    Some months ago, I participated in a two-week experiment that involved using a smartphone app to track every morsel of food I ate, every beverage I drank and every medication I took, as well as how much I slept and exercised. I wore a sensor that monitored my blood-glucose levels, and I sent in a sample of my stool for an assessment of my gut microbiome. All of my data, amassed with similar input from more than a thousand other people, was analyzed by artificial intelligence to create a personalized diet algorithm. The point was to find out what kind of food I should be eating to live a longer and healthier life...
  • Neural MMO — A Massively Multiagent Game Environment
    We’re releasing a Neural MMO — a massively multiagent game environment for reinforcement learning agents. Our platform supports a large, variable number of agents within a persistent and open-ended task. The inclusion of many agents and species leads to better exploration, divergent niche formation, and greater overall competence...
  • Learning to navigate in cities without a map
    We present an interactive navigation environment that uses first-person perspective photographs from Google Street View, approved for use by the StreetLearn project and academic research, and gamify that environment to train an AI...
  • Model-Based Reinforcement Learning for Atari
    In this paper, we explore how video prediction models can similarly enable agents to solve Atari games with orders of magnitude fewer interactions than model-free methods. We describe Simulated Policy Learning (SimPLe), a complete model-based deep RL algorithm based on video prediction models and present a comparison of several model architectures, including a novel architecture that yields the best results in our setting. Our experiments evaluate SimPLe on a range of Atari games and achieve competitive results with only 100K interactions between the agent and the environment (400K frames), which corresponds to about two hours of real-time play...
  • Microsoft Excel will now let you snap a picture of a spreadsheet and import it
    Microsoft is adding a very useful feature to its Excel mobile apps for iOS and Android. It allows Excel users to take a photo of a printed data table and convert it into a fully editable table in the app. This feature is rolling out initially in the Android Excel app, before making its way to iOS soon. Microsoft is using artificial intelligence to implement this feature, with image recognition so that Excel users don’t have to manually input hardcopy data...
  • VideoFlow: A Flow-Based Generative Model for Video
    In this work, we propose a model for video prediction based on normalizing flows, which allows for direct optimization of the data likelihood, and produces high-quality stochastic predictions. To our knowledge, our work is the first to propose multi-frame video prediction with normalizing flows. We describe an approach for modeling the latent space dynamics, and demonstrate that flow-based generative models offer a viable and competitive approach to generative modeling of video...
  • High-Fidelity Image Generation With Fewer Labels
    In this work we demonstrate how one can benefit from recent work on self- and semi-supervised learning to outperform state-of-the-art (SOTA) on both unsupervised ImageNet synthesis, as well as in the conditional setting. In particular, the proposed approach is able to match the sample quality (as measured by FID) of the current state-of-the art conditional model BigGAN on ImageNet using only 10% of the labels and outperform it using 20% of the labels...
 
 

Event

 

 
MIT Robo-AI Exchange

The MIT Robo-AI Exchange (March 9, 2019) will bring together business leaders from across a number of industries to share strategies and outcomes related to the adoption of Robotics and AI. The event attracts business executives, corporate strategists, product and project managers, university students, entrepreneurs, technologists and academics to learn from world-class keynote speakers and panelists as well as one another.

Use promo code BNT982 at https://robo-ai.org for 20% off professional tickets.
 

Want to post an event here? Email us for details >> team@datascienceweekly.org
 
 

Jobs

 
  • Data Scientist - Disney Streaming - NYC

    The Data Scientist is a critical position within DSS and in the Data organization who specializes in applying machine learning methods to meet optimization, personalization, recommendations and efficiency related challenges, in close collaboration with engineering and business partners. In this role, you will build and apply machine learning techniques and modern statistics to data both augment decision-making but to also significantly improve operational process problems through automation. You will collaborate across teams to define problems and develop automated solutions with the Data, Product and Engineering teams to be built into our products...

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

 

Training & Resources

 
  • Modern Deep Learning Techniques Applied to Natural Language Processing
    This project contains an overview of recent trends in deep learning based natural language processing (NLP). It covers the theoretical descriptions and implementation details behind deep learning models, such as recurrent neural networks (RNNs), convolutional neural networks (CNNs), and reinforcement learning, used to solve various NLP tasks and applications. The overview also contains a summary of state of the art results for NLP tasks such as machine translation, question answering, and dialogue systems...
  • TF-Replicator: Distributed Machine Learning for Researchers
    Today, we are excited to share how we developed TF-Replicator, a software library that helps researchers deploy their TensorFlow models on GPUs and Cloud TPUs with minimal effort and no previous experience with distributed systems...
 
 

Books

 

 
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.