This is an implementation of the LFADS model (https://github.com/tensorflow/models/tree/master/research/lfads) along with coordinated dropout and sample validation techniques described in "Enabling hyperparameter optimization in sequential autoencoders for spiking neural data", Mohammad Reza Keshtkaran, Chethan Pandarinath, NeurIPS 2019 (https://papers.nips.cc/paper/9722-enabling-hyperparameter-optimization-in-sequential-autoencoders-for-spiking-neural-data)