Here are some good machine learning resources.
- The Unreasonable Effectiveness of Recurrent Neural Networks: http://karpathy.github.io/2015/05/21/rnn-effectiveness/
- Stanford deep learning for NLP (lecture notes): https://cs224d.stanford.edu/lecture_notes/
- NTU deep learning (lecture notes): http://speech.ee.ntu.edu.tw/~tlkagk/courses_MLDS17.html
- LSTM Hello World: https://medium.com/towards-data-science/lstm-by-example-using-tensorflow-feb0c1968537
- HBO’s Silicon Valley “Not Hotdog”: https://medium.com/@timanglade/how-hbos-silicon-valley-built-not-hotdog-with-mobile-tensorflow-keras-react-native-ef03260747f3
- Use the TimeDistributed Layer for LSTM: https://machinelearningmastery.com/timedistributed-layer-for-long-short-term-memory-networks-in-python/
- Deep learning intro: https://medium.com/machine-learning-for-humans/neural-networks-deep-learning-cdad8aeae49b
A while back, I created a platform to track and rank the content linked from the 8,000 daily tweets that are tagged #machineLearning. It filters and ranks the most popular shared content in realtime. Machine learning’s zeitgeist, you might say. It’s been running for over a year, monitoring half a billion tweets a day on dozens of topics, and will always be free to use. No ads. No BS. See http://theherdlocker.com/tweet/popularity/machinelearning