Paper Info
Title
A Deep Predictive Coding Network For Inferring Hierarchical Causes Underlying Sensory Inputs
Abstract
Predictive coding has been argued as a mechanism underlying sensory processing in the brain. In computational models of predictive coding, the brain is described as a machine that constructs and continuously adapts a generative model based on the stimuli received from external environment. It uses this model to infer causes that generated the received stimuli. However, it is not clear how predictive coding can be used to construct deep neural network models of the brain while complying with the architectural constraints imposed by the brain. Here, we describe an algorithm to construct a deep generative model that can be used to infer causes behind the stimuli received from external environment. Specifically, we train a deep neural network on real-world images in an unsupervised learning paradigm. To understand the capacity of the network with regards to modeling the external environment, we studied the causes inferred using the trained model on images of objects that are not used in training. Despite the novel features of these objects the model is able to infer the causes for them. Furthermore, the reconstructions of the original images obtained from the generative model using these inferred causes preserve important details of these objects.
Year
DOI
Venue
2018
10.1007/978-3-030-01424-7_45
ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2018, PT III
Keywords
Field
DocType
Predictive coding, Deep generative models
Pattern recognition,Computer science,Predictive coding,Unsupervised learning,Computational model,Artificial intelligence,Stimulus (physiology),Sensory system,Artificial neural network,Machine learning,Generative model,Sensory processing
Conference
Volume
ISSN
Citations 
11141
0302-9743
0
PageRank 
References 
Authors
0.34
7
3
Name
Order
Citations
PageRank
Shirin Dora1343.38
Cyriel Pennartz270.99
Sander Bohte3193.21