Position-wise optimizer: A nature-inspired optimization algorithm
The human nervous system utilizes synaptic plasticity to solve optimization problems. Previous studies have tried to add the plasticity factor to the training process of artificial neural networks, but most of those models require complex external control over the network or complex novel rules. In this manuscript, a novel nature-inspired optimization algorithm is introduced that imitates biological neural plasticity. Furthermore, the model is tested on three datasets and the results are compared with gradient descent optimization.
PDF Abstract
CIFAR-10
MNIST
Results from the Paper
| Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
|---|---|---|---|---|---|---|
| Nature-Inspired Optimization Algorithm | CIFAR-10 | Gradient descent optimizer | training time (s) | 50 | # 2 | |
| Nature-Inspired Optimization Algorithm | CIFAR-10 | Position-wise optimizer | training time (s) | 23 | # 1 | |
| Nature-Inspired Optimization Algorithm | MNIST | Position-wise optimizer | training time (s) | 227 | # 1 | |
| Nature-Inspired Optimization Algorithm | MNIST | Gradient descent optimizer | training time (s) | 282 | # 2 |
Methods
No methods listed for this paper. Add
relevant methods here
