Phil 2.8.19

7:00 – 6:00 ASRC IRAD TL

  • Need to ping Eric about tasking. Suggest time series prediction. Speaking of which, Transformers (post 1 and post 2) may be much better than LSTMs for series prediction.
    • The Transformer model in Attention is all you need:a Keras implementation.
      • A Keras+TensorFlow Implementation of the Transformer: “Attention is All You Need” (Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, Illia Polosukhin, arxiv, 2017)
    • keras-transformer 0.17.0
      • Implementation of transformer for translation-like tasks.
    • The other option is “teachable” ML systems using evolution. There is a lot of interesting older work in this area:
      • Particle swarms for feedforward neural network training
      • Evolving artificial neural networks
      • Training Feedforward Neural Networks Using Genetic Algorithms.
        • Multilayered feedforward neural networks possess a number of properties which make them particularly suited to complex pattern classification problems. However, their application to some real world problems has been hampered by the lack of a training algorithm which reliably finds a nearly globally optimal set of weights in a relatively short time. Genetic algorithms are a class of optimization procedures which are good at exploring a large and complex space in an intelligent way to find values close to the global optimum. Hence, they are well suited to the problem of training feedforward networks. In this paper, we describe a set of experiments performed on data from a sonar image classification problem. These experiments both 1) illustrate the improvements gained by using a genetic algorithm rather than backpropagation and 2) chronicle the evolution of the performance of the genetic algorithm as we added more and more domain-specific knowledge into it.
  • Add writing to the db from within the program, download the latest slack bundle, and try storing it!
  • Read in test-dungeon-1 and realized that there is no explicit link between the channel and the message in the data, so I added fields for the current directory and the current file
  • Ok, everything seems to be working. I had a few trips around the block getting a unique id for messages, but that seems ok now.
  • Created view(s), where I learned how to use conditionals and was happy:
    SELECT * FROM t_message;
    SELECT * FROM t_message_files;
    CREATE or REPLACE VIEW user_view AS
    SELECT,, p.real_name,
           (CASE WHEN p.display_name > '' THEN p.display_name ELSE END) as username
    FROM t_user u
           INNER JOIN t_user_profile p ON = p.parent_id;
    select * from user_view;
    CREATE or REPLACE VIEW post_view AS
    SELECT FROM_UNIXTIME(p.ts) as post_time, p.dirname as post_topic, p.text as post_text, u.username,
           (CASE WHEN p.subtype > '' THEN p.subtype ELSE p.type END) as type
    FROM t_message p
           INNER JOIN user_view u ON p.user =;
    select * from post_view order by post_time limit 1000;


  • Need to put together a strawman invitation that also has checkboxes for BB-based and/or Slack-based preferences and why a user might choose one over the other. Nope, not yet
  • Got the Slack academic discount!