Michael J Clark

Attempting to replicate "A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem" https://arxiv.org/abs/1706.10059 (and an openai gym environment)

wassname

A website to find long-tail keywords using search suggestions

wassname

Videos of deep learning optimizers moving on 3D problem-landscapes

wassname

implementing "recurrent attentive neural processes" to forecast power usage (w. LSTM baseline, MCDropout)

wassname

Detect water leaks from satellite images using machine learning

wassname

Teaching machines to spell with deep learning (acc=>80%) e.g. a model hears "pɹˈaʊd˺ɚ" and writes "prowder" (but it should be "prouder")

wassname

Attempt at reinforcement learning with curiosity for Sonic the Hedgehog games. Number 149 on OpenAI retro contest leaderboard, but more work needed

wassname