Dendrite Net with Acceleration Module for Faster Nonlinear Mapping and System Identification

Abstract

Nonlinear mapping is an essential and common demand in online systems, such as sensor systems and mobile phones. Accelerating nonlinear mapping will directly speed up online systems. Previously the authors of this paper proposed a Dendrite Net (DD) with enormously lower time complexity than the existing nonlinear mapping algorithms; however, there still are redundant calculations in DD. This paper presents a DD with an acceleration module (AC) to accelerate nonlinear mapping further. We conduct three experiments to verify whether DD with AC has lower time complexity while retaining DD’s nonlinear mapping properties and system identification properties: The first experiment is the precision and identification of unary nonlinear mapping, reflecting the calculation performance using DD with AC for basic functions in online systems. The second experiment is the mapping precision and identification of the multi-input nonlinear system, reflecting the performance for designing online systems via DD with AC. Finally, this paper compares the time complexity of DD and DD with AC and analyzes the theoretical reasons through repeated experiments. Results: DD with AC retains DD’s excellent mapping and identification properties and has lower time complexity. Significance: DD with AC can be used for most engineering systems, such as sensor systems, and will speed up computation in these online systems.

A Dendrite Net based decoupled framework for the reliability‐based control co‐design problem

“…In the architecture of DD Net, there are many parameters that should be adjusted, such as the size of training data in one batch 𝑚, the learning rate 𝛼, the training times 𝑇, and the number of DD modules 𝑁. According to Ref., 34,35 𝑚 depends on the size of the total training data; 𝛼 can either be changed adaptively from an initial large value to a small one or fixed to a small value iterated by heuristics algorithm; 𝑇 can be assigned to a large number, and then determine whether to stop training according to the training error; 𝑁 is the most significant parameter since it directly determines the accuracy and complexity of DD model, and the prediction accuracy of DD model improves as 𝑁 increases.…”

“…DD Net is a white‐box machine learning algorithm proposed by Liu 34,35 based on the theory that biological dendrites in brains also exist and∖or∖not operations 36 . The overall architecture of DD Net is shown in Figure 1, the last unit is a linear module and others are DD modules, training data is fed to all computing units.…”