How do neurons operate on sparse distributed representations? A mathematical theory of sparsity, neurons and active dendrites

Abstract

We propose a formal mathematical model for sparse representations and active dendrites in neocortex. Our model is inspired by recent experimental findings on active dendritic processing and NMDA spikes in pyramidal neurons. These experimental and modeling studies suggest that the basic unit of pattern memory in the neocortex is instantiated by small clusters of synapses operated on by localized non-linear dendritic processes. We derive a number of scaling laws that characterize the accuracy of such dendrites in detecting activation patterns in a neuronal population under adverse conditions. We introduce the union property which shows that synapses for multiple patterns can be randomly mixed together within a segment and still lead to highly accurate recognition. We describe simulation results that provide further insight into sparse representations as well as two primary results. First we show that pattern recognition by a neuron with active dendrites can be extremely accurate and robust with high dimensional sparse inputs even when using a tiny number of synapses to recognize large patterns. Second, equations representing recognition accuracy of a dendrite predict optimal NMDA spiking thresholds under a generous set of assumptions. The prediction tightly matches NMDA spiking thresholds measured in the literature. Our model matches many of the known properties of pyramidal neurons. As such the theory provides a mathematical framework for understanding the benefits and limits of sparse representations in cortical networks.

Journal submission, under review

Cited by in corpus (12)

• Continuous online sequence learning with an unsupervised neural network model
• Continual Learning for Recurrent Neural Networks: an Empirical Evaluation
• Real-Time Anomaly Detection for Streaming Analytics
• How Can We Be So Dense? The Benefits of Using Highly Sparse Representations
• Avoiding Catastrophe: Active Dendrites Enable Multi-Task Learning in Dynamic Environments
• Sequence learning, prediction, and replay in networks of spiking neurons
• End-to-End Memristive HTM System for Pattern Recognition and Sequence Prediction
• Using Spatial Pooler of Hierarchical Temporal Memory to classify noisy videos with predefined complexity
• Application of Hierarchical Temporal Memory Theory for Document Categorization
• The observer-assisted method for adjusting hyper-parameters in deep learning algorithms
• Theory of Generative Deep Learning : Probe Landscape of Empirical Error via Norm Based Capacity Control
• Formation of cell assemblies with iterative winners-take-all computation and excitation-inhibition balance