A neuro-inspired architecture for unsupervised continual learning based on online clustering and hierarchical predictive coding
This work addresses continual learning for AI systems, but it is incremental as it builds on existing neuroscience-inspired approaches without presenting new empirical validation.
The authors tackled the problem of continual learning by proposing a neuro-inspired architecture based on online clustering and hierarchical predictive coding, but no experimental results or concrete numbers are provided as they are deferred to a future extended version.
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.