mlsanityData to 7 Oct 2026

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

arXiv 2512.04094 ↗First posted 20 Nov 2025cs.NE cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 18 of its 41 references that are in the map. First posted on arXiv 20 Nov 2025.

Builds on

18 of 41 references.

References · 18

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  4. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  5. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  6. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  7. 2020Longformer: The Long-Document Transformercited by 3,362
  8. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,141
  9. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 1,981
  10. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,654
  11. 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,447
  12. 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 869
6 more
  1. 2019Surrogate Gradient Learning in Spiking Neural Networkscited by 604
  2. 2020Time Series Forecasting With Deep Learning: A Surveycited by 457
  3. 2018The UCR Time Series Archivecited by 421
  4. 2021Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Bettercited by 153
  5. 2020Dendrite Net: A White-Box Module for Classification, Regression, and System Identificationcited by 11
  6. 2024Dendrites endow artificial neural networks with accurate, robust and parameter-efficient learningcited by 7

Built on by

Not cited yet.