Timothy Yu
Timothy Yu
related to #26
related to https://github.com/timothyyu/gdax-orderbook-ml/issues/49
Parallelization of input for non-sequential model (conceptual, still testing/under development): https://github.com/timothyyu/lstm-breaker  
lambada function + attention mechanism potential https://github.com/philipperemy/keras-attention-mechanism
related to #25, #38, #26, #22
related to #48, #49, and #23 and #33 in implementation/data pipeline relevant
monitor memory during scrape to keep resource use in check
mlab for remote mongodb hosting (heroku, mlab, flask) example: https://github.com/AiyanaLizMathew/JobFitt/blob/master/Sandbox/app.py
Semi/psuedo supervised learning + reinforcement learning would be ideal, but there is a list of issues that have to be addressed first (even before the hosted model stage) to get...
potential for model to run entirely in js with node backend with keras.js