# Neuromemrisitive Architecture of HTM with On-Device Learning and Neurogenesis

## TL;DR

This paper introduces a neuromemristive architecture for Hierarchical Temporal Memory (HTM) that enables on-device learning, neurogenesis, and robust image recognition, optimized for mobile platforms.

## Contribution

It presents a novel memristor-based crossbar architecture for HTM's spatial pooler, incorporating neurogenesis and plasticity mechanisms for improved robustness and efficiency.

## Key findings

- Supports rapid on-chip training within 2 clock cycles
- Achieves robustness in image recognition tasks with MNIST and Yale datasets
- Demonstrates low power consumption suitable for mobile devices

## Abstract

Hierarchical temporal memory (HTM) is a biomimetic sequence memory algorithm that holds promise for invariant representations of spatial and spatiotemporal inputs. This paper presents a comprehensive neuromemristive crossbar architecture for the spatial pooler (SP) and the sparse distributed representation classifier, which are fundamental to the algorithm. There are several unique features in the proposed architecture that tightly link with the HTM algorithm. A memristor that is suitable for emulating the HTM synapses is identified and a new Z-window function is proposed. The architecture exploits the concept of synthetic synapses to enable potential synapses in the HTM. The crossbar for the SP avoids dark spots caused by unutilized crossbar regions and supports rapid on-chip training within 2 clock cycles. This research also leverages plasticity mechanisms such as neurogenesis and homeostatic intrinsic plasticity to strengthen the robustness and performance of the SP. The proposed design is benchmarked for image recognition tasks using MNIST and Yale faces datasets, and is evaluated using different metrics including entropy, sparseness, and noise robustness. Detailed power analysis at different stages of the SP operations is performed to demonstrate the suitability for mobile platforms.