• VisualizeMnist:
  Real-time visualization of a network recognizing digits from user's input.
  I trained a network using MNIST dataset and parsed the weight data in python. With this data, I implemented my own custom functions that are needed to run the network in Processing including matrix multiplication function, activation functions. At first trial, because MNIST dataset is preprocessed for numbers to be in the center of the images, there was a precision problem when the user's input is placed little bit far away from the center. I used data augmentation technic in the training process to resolve this problem...

• Visualizing 150000 butterflies from the Natural History Museum
  The Natural History Museum in London has a data portal in which they provide digital records for many of their specimens. Some of these records have images. I recently learned how to use machine learning tools such as convolutional neural networks and I wanted to use the NHM data to see what can be done with these tools. The dataset of butterflies seemed particularly interesting to me because the images are visually interesting, yet they are all similar in that they all contain a butterfly in a canonical pose...

• Acoustic activity recognition in JavaScript
  Acoustic activity recognition is using the rich properties of sound to gain insights about an environment or activity. This can be used to enhance smart systems and build more personalised connected homes. Researchers at the CMU used Python to prototype their experiments and made their project open-source on Github if you want to have a look but I wanted to see if I could reproduce something similar using web technologies, and it worked! ...

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.

• AI Debate 2019: Yoshua Bengio vs Gary Marcus
  This is an AI Debate between Yoshua Bengio and Gary Marcus from Dec 23, 2019, organized by Montreal.AI and Mila - Institut Québécois d'Intelligence Artificielle...

• Facebook, Carnegie Mellon build first AI that beats pros in 6-player poker
  Pluribus is the first AI bot capable of beating human experts in six-player no-limit Hold’em, the most widely played poker format in the world. This is the first time an AI bot has beaten top human players in a complex game with more than two players or two teams. We tested Pluribus against professional poker players, including two winners of the World Series of Poker Main Event. Pluribus won decisively...

• Key AI and Data Trends for 2020
  The Data Exchange Podcast: Mikio Braun and Ben Lorica on tools, models, applications, and risks to look out for in 2020...

• This AI researcher is trying to ward off a reproducibility crisis
  Joelle Pineau doesn’t want science’s reproducibility crisis to come to artificial intelligence (AI). Spurred by her frustration with difficulties recreating results from other research teams, Pineau, a machine-learning scientist at McGill University and Facebook in Montreal, Canada, is now spearheading a movement to get AI researchers to open up their methods and code to scrutiny...

• Mastering Complex Control in MOBA Games with Deep Reinforcement Learning
  We study the reinforcement learning problem of complex action control in the Multi-player Online Battle Arena (MOBA) 1v1 games. This problem involves far more complicated state and action spaces than those of traditional 1v1 games, such as Go and Atari series, which makes it very difficult to search any policies with human-level performance. In this paper, we present a deep reinforcement learning framework to tackle this problem from the perspectives of both system and algorithm. Our system is of low coupling and high scalability, which enables efficient explorations at large scale. Our algorithm includes several novel strategies, including control dependency decoupling, action mask, target attention, and dual-clip PPO...

• Measuring Arithmetic Extrapolation Performance
  The Neural Arithmetic Logic Unit (NALU) is a neural network layer that can learn exact arithmetic operations between the elements of a hidden state. The goal of NALU is to learn perfect extrapolation, which requires learning the exact underlying logic of an unknown arithmetic problem. Evaluating the performance of the NALU is non-trivial as one arithmetic problem might have many solutions. As a consequence, single-instance MSE has been used to evaluate and compare performance between models. However, it can be hard to interpret what magnitude of MSE represents a correct solution and models sensitivity to initialization. We propose using a success-criterion to measure if and when a model converges...

• Adversarial Representation Active Learning
  Active learning aims to develop label-efficient algorithms by querying the most informative samples to be labeled by an oracle. The design of efficient training methods that require fewer labels is an important research direction that allows more effective use of computational and human resources for labeling and training deep neural networks. In this work, we demonstrate how we can use recent advances in deep generative models, to outperform the state-of-the-art in achieving the highest classification accuracy using as few labels as possible...

• Playing Text-Adventure Games with Graph-Based Deep Reinforcement Learning
  Text-based adventure games provide a platform on which to explore reinforcement learning in the context of a combinatorial action space, such as natural language. We present a deep reinforcement learning architecture that represents the game state as a knowledge graph which is learned during exploration. This graph is used to prune the action space, enabling more efficient exploration...

• Four lessons I learned after my first full-time job after college
  Last year, I wrote Career advice for recent Computer Science graduates about the decision-making process I went over when choosing my first full-time job after college. Now that I’ve just left that first job, I want to share some lessons that I wish I knew when I started...

 
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!

• Manager, Data Science - JetBlue - Long Island City, NY
  
  JetBlue is seeking a Data Science Manager to lead a team of data scientists who will design experiments and develop machine learning models to address the company’s most complex data problems. We are looking for an experienced data scientist with broad knowledge of machine learning and statistical techniques. This individual will establish best practices for data science workflows and knows how to create an environment that enables data scientists to perform at their best. Beyond a great culture, the benefits (free flights!) are hard to beat...

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

• A Gentle Introduction To Math Behind Neural Networks
  I ignored understanding the Math behind neural networks and Deep Learning for a long time as I didn’t have good knowledge of algebra or differential calculus. Few days ago, I decided to to start from scratch and derive the methodology and Math behind neural networks and Deep Learning, to know how and why they work. I also decided to write this article, which would be useful to people like me, who finds it difficult to understand these concepts...

• An Inquiry into Matplotlib's Figures, Axes, subplots and the very amazing GridSpec!
  This article attempts to explain the workings of some of the foundations of any plot you create using matplotlib. We will mostly refrain from focusing on what data we are plotting and instead focus on the anatomy of our plots...

• Multiplicative Interactions and Where to Find Them
  We explore the role of multiplicative interaction as a unifying framework to describe a range of classical and modern neural network architectural motifs, such as gating, attention layers, hypernetworks, and dynamic convolutions amongst others...

• 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
  .
    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