Pyramidal Predictive Network: A Model for Visual-frame Prediction Based on Predictive Coding Theory

by   Chaofan Ling, et al.

Visual-frame prediction is a pixel-dense prediction task that infers future frames from past frames. Lacking of appearance details, low prediction accuracy and high computational overhead are still major problems with current models or methods. In this paper, we propose a novel neural network model inspired by the well-known predictive coding theory to deal with the problems. Predictive coding provides an interesting and reliable computational framework, which will be combined with other theories such as the cerebral cortex at different level oscillates at different frequencies, to design an efficient and reliable predictive network model for visual-frame prediction. Specifically, the model is composed of a series of recurrent and convolutional units forming the top-down and bottom-up streams, respectively. The update frequency of neural units on each of the layer decreases with the increasing of network levels, which results in neurons of higher-level can capture information in longer time dimensions. According to the experimental results, this model shows better compactness and comparable predictive performance with existing works, implying lower computational cost and higher prediction accuracy. Code is available at


page 1

page 4

page 8

page 9

page 11


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

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

Analyzing and Improving the Pyramidal Predictive Network for Future Video Frame Prediction

The pyramidal predictive network (PPNV1) proposes an interesting tempora...

Encoding Longer-term Contextual Multi-modal Information in a Predictive Coding Model

Studies suggest that within the hierarchical architecture, the topologic...

Exploring Spatial-Temporal Multi-Frequency Analysis for High-Fidelity and Temporal-Consistency Video Prediction

Video prediction is a pixel-wise dense prediction task to infer future f...

Modeling sequential data using higher-order relational features and predictive training

Bi-linear feature learning models, like the gated autoencoder, were prop...

Relating Human Perception of Musicality to Prediction in a Predictive Coding Model

We explore the use of a neural network inspired by predictive coding for...

Predictive Coding-based Deep Dynamic Neural Network for Visuomotor Learning

This study presents a dynamic neural network model based on the predicti...

Please sign up or login with your details

Forgot password? Click here to reset