pydata

Keep Looking, Don't Settle

2019-03-09 Week 10

Shares From Internet

  1. How to Develop a Word Embedding Model for Predicting Movie Review Sentiment: introduce how to do word embedding in keras and gensim and compare their performance on the movie review data.
  2. Ludwig: a toolbox from uber that allows you to train and test deep learning models without writing code. Ludwig is build on top of Tensorflow.
  3. m2cgen: Model2Code Generator is a lightweight tool to convert your model to C, python or java. Most tree-based models are supported.
  4. This choice is the key to success: Choosing to work hard is key when it comes to being successful, according to Jeff Bezos.
  5. How to speak like a leader, not like an engineer?. Some useful suggestions: (1) communicate in the language of options, not demands. (2) summarize your choices, decisions and solutions in high level language from the perspective of what they care about.
  6. Why do we need to set the gradients manually to zero in pytorch?