Data Science & Machine Learning Newsletter # 99

Posted on Fri 28 July 2017 in Data Science & Machine Learning Newsletter


You want to get updates? Please join Data Science & Machine Learning Newsletter Linked Group


  • Ultimate Guide To Statistical Significance Tests in R
    • Implement and interpret the commonly used statistical significance tests in R, the purpose, when to use and how to interpret the result.
  • Word2Vec (skip-gram model)
    • The skip-gram neural network model is actually surprisingly simple in its most basic form. Train a simple neural network with a single hidden layer to perform a certain task, but then we’re not actually going to use that neural network for the task we trained it on! Instead, the goal is actually just to learn the weights of the hidden layer–we’ll see that these weights are actually the “word vectors” that we’re trying to learn.
    • Part 1
    • Part 2
  • Artificial intelligence suggests recipes based on food photos
    • Researchers from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) believe that analyzing photos like these could help us learn recipes and better understand people's eating habits. In a new paper with the Qatar Computing Research Institute (QCRI), the team trained an artificial intelligence system called Pic2Recipe to look at a photo of food and be able to predict the ingredients and suggest similar recipes.
  • Comparing Different Species of Cross-Validation

    [caption id="attachment_2325" align="alignright" width="300"]sciblox sciblox[/caption]

  • https://github.com/danielhanchen/sciblox
    • An all in one Python3 Data Science Package. Easy visualisation, data mining, data preparation and machine learning.
  • DARLA: Improving Zero-Shot Transfer in Reinforcement Learning
    • Domain adaptation is an important open problem in deep reinforcement learning (RL). In many scenarios of interest data is hard to obtain, so agents may learn a source policy in a setting where data is readily available, with the hope that it generalises well to the target domain. We propose a new multi-stage RL agent, DARLA (DisentAngled Representation Learning Agent), which learns to see before learning to act.
  • How to squeeze the most from your training data
    • In many cases, getting enough well-labelled training data is a huge hurdle for developing accurate prediction systems. Here is an innovative approach which uses SVM to get the most from training data.
  • The Truth About Bayesian Priors and Overfitting
    • Many of the considerations we will run through will be directly applicable to your everyday life of applying Bayesian methods to your specific domain.