Multi Resolution LSTM For Long Term Prediction In Neural Activity Video

by   Yilin Song, et al.

Epileptic seizures are caused by abnormal, overly syn- chronized, electrical activity in the brain. The abnor- mal electrical activity manifests as waves, propagating across the brain. Accurate prediction of the propagation velocity and direction of these waves could enable real- time responsive brain stimulation to suppress or prevent the seizures entirely. However, this problem is very chal- lenging because the algorithm must be able to predict the neural signals in a sufficiently long time horizon to allow enough time for medical intervention. We consider how to accomplish long term prediction using a LSTM network. To alleviate the vanishing gradient problem, we propose two encoder-decoder-predictor structures, both using multi-resolution representation. The novel LSTM structure with multi-resolution layers could significantly outperform the single-resolution benchmark with similar number of parameters. To overcome the blurring effect associated with video prediction in the pixel domain using standard mean square error (MSE) loss, we use energy- based adversarial training to improve the long-term pre- diction. We demonstrate and analyze how a discriminative model with an encoder-decoder structure using 3D CNN model improves long term prediction.


page 4

page 6

page 8


Predictive Coding Based Multiscale Network with Encoder-Decoder LSTM for Video Prediction

We are introducing a multi-scale predictive model for video prediction h...

Diversity encouraged learning of unsupervised LSTM ensemble for neural activity video prediction

Being able to predict the neural signal in the near future from the curr...

Unsupervised Learning of Long-Term Motion Dynamics for Videos

We present an unsupervised representation learning approach that compact...

Hierarchical Model for Long-term Video Prediction

Video prediction has been an active topic of research in the past few ye...

Hierarchical Long-term Video Prediction without Supervision

Much of recent research has been devoted to video prediction and generat...

PredRNN++: Towards A Resolution of the Deep-in-Time Dilemma in Spatiotemporal Predictive Learning

We present PredRNN++, an improved recurrent network for video predictive...

Characterization of singular flows of zeroth-order pseudo-differential operators via elliptic eigenfunctions: a numerical study

The propagation of internal gravity waves in stratified media, such as t...

Please sign up or login with your details

Forgot password? Click here to reset