A neuro-inspired architecture for unsupervised continual learning based on online clustering and hierarchical predictive coding

2018/10/22 by Constantine Dovrolis, Dovrolis, Constantine
Biochemistry, Genetics and Molecular Biology · Computer Science · Mathematics · Neuroscience · #Anomaly Detection Techniques and Applications #Cognitive Science and Education Research #Neural Networks and Applications #cs.AI #cs.LG #q-bio.NC #stat.ML

paper · pdf · doi:10.48550/arxiv.1810.09391

Under peer-review

arxiv created 2018/10/22 · arxiv updated 2018/10/23

Abstract

We propose that the Continual Learning desiderata can be achieved through a neuro-inspired architecture, grounded on Mountcastle's cortical column hypothesis. The proposed architecture involves a single module, called Self-Taught Associative Memory (STAM), which models the function of a cortical column. STAMs are repeated in multi-level hierarchies involving feedforward, lateral and feedback connections. STAM networks learn in an unsupervised manner, based on a combination of online clustering and hierarchical predictive coding. This short paper only presents the architecture and its connections with neuroscience. A mathematical formulation and experimental results will be presented in an extended version of this paper.

Citations

• NEURONAL CIRCUITS OF THE NEOCORTEX

Related

• Unsupervised Progressive Learning and the STAM Architecture
• Neuro-mimetic Task-free Unsupervised Online Learning with Continual Self-Organizing Maps
• Lifelong Neural Predictive Coding: Learning Cumulatively Online without Forgetting
• On-the-Fly Learning in a Perpetual Learning Machine
• Encoding Reality: Prediction-Assisted Cortical Learning Algorithm in Hierarchical Temporal Memory