Architecture of a Cortex Inspired Hierarchical Event Recaller
Valentin Puente Varona

TL;DR
This paper introduces a biologically inspired hierarchical model for unsupervised, continuous learning and prediction of complex temporal patterns, demonstrated on human speech recognition without prior training.
Contribution
A novel cerebellar cortex-inspired architecture capable of learning and predicting complex temporal sequences with minimal training data.
Findings
Successfully learned and predicted human speech patterns from raw data.
Performed well with reduced training sets compared to traditional ML.
Potential for low-cost hardware implementation.
Abstract
This paper proposes a new approach to Machine Learning (ML) that focuses on unsupervised continuous context-dependent learning of complex patterns. Although the proposal is partly inspired by some of the current knowledge about the structural and functional properties of the mammalian brain, we do not claim that biological systems work in an analogous way (nor the opposite). Based on some properties of the cerebellar cortex and adjacent structures, a proposal suitable for practical problems is presented. A synthetic structure capable of identifying and predicting complex temporal series will be defined and experimentally tested. The system relies heavily on prediction to help identify and learn patterns based on previously acquired contextual knowledge. As a proof of concept, the proposed system is shown to be able to learn, identify and predict a remarkably complex temporal series such…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsScientific Computing and Data Management · Distributed and Parallel Computing Systems · Parallel Computing and Optimization Techniques
MethodsSparse Evolutionary Training
