Hamiltonian Neural Networks · HackerPapers discussions

Hamiltonian Neural Networks — mentioned by ylem

Tue, 21 Jul 2020 18:57:49 GMT

There were some interesting talks on neural differentiation applied to physics at ICLR. You probably saw: https://arxiv.org/abs/1906.01563 Very fun!

Paper and discussion history. A mention is not an endorsement.

Hamiltonian Neural Networks — mentioned by seesawtron

Tue, 23 Jun 2020 21:15:41 GMT

Hamiltonian NNs are not a new thing. There was a NIPS 2019 paper [0] that attempted to do that same for some toy problems. In general the idea of including model or context-based information into neural networks goes along the line of Kahneman's System I and System II of the human mind. System I is the "emotional" brain that is fast and makes decisions quickly while System II is the "rational" brain that is slow and expensive and takes time to compute a response. Researchers have been trying to develop ML models that utilize this dichotomy by building corresponding dual modules but the major…

Paper and discussion history. A mention is not an endorsement.

Hamiltonian Neural Networks — mentioned by shoyer

Thu, 06 Feb 2020 18:43:09 GMT

It's actually extraordinarily difficult to get a DNN model to accurately predict planetary motion over arbitrary time horizons. RNNs have a tendency to either decay or blow-up. The only way I know to make neural nets work well for this problem is to build in lots of physics into the model architecture, e.g., conservation of energy: https://arxiv.org/abs/1906.01563

Paper and discussion history. A mention is not an endorsement.