Memory-DD: A Low-Complexity Dendrite-Inspired Neuron for Temporal Prediction Tasks

TL;DR

Memory-DD is a novel low-complexity dendrite-inspired neuron model designed for temporal sequence prediction, outperforming traditional models like LSTM in accuracy and efficiency on benchmark datasets.

Contribution

This paper introduces Memory-DD, a new dendrite-inspired neuron architecture specifically tailored for temporal data prediction, combining low complexity with high performance.

Findings

Achieves 89.41% accuracy on temporal classification benchmarks.

Uses 50% fewer parameters than LSTM.

Reduces computational complexity by 27.7%.

Abstract

Dendrite-inspired neurons have been widely used in tasks such as image classification due to low computational complexity and fast inference speed. Temporal data prediction, as a key machine learning task, plays a key role in real-time scenarios such as sensor data analysis, financial forecasting, and urban traffic management. However, existing dendrite-inspired neurons are mainly designed for static data. Studies on capturing dynamic features and modeling long-term dependencies in temporal sequences remain limited. Efficient architectures specifically designed for temporal sequence prediction are still lacking. In this paper, we propose Memory-DD, a low-complexity dendrite-inspired neuron model. Memory-DD consists of two dendrite-inspired neuron groups that contain no nonlinear activation functions but can still realize nonlinear mappings. Compared with traditional neurons without dendritic functions, Memory-DD requires only two neuron groups to extract logical relationships between features in input sequences. This design effectively captures temporal dependencies and is suitable for both classification and regression tasks on sequence data. Experimental results show that Memory-DD achieves an average accuracy of 89.41% on 18 temporal classification benchmark datasets, outperforming LSTM by 4.25%. On 9 temporal regression datasets, it reaches comparable performance to LSTM, while using only 50% of the parameters and reducing computational complexity (FLOPs) by 27.7%. These results demonstrate that Memory-DD successfully extends the low-complexity advantages of dendrite-inspired neurons to temporal prediction, providing a low-complexity and efficient solution for time-series data processing.