Exploring the Imposition of Synaptic Precision Restrictions For Evolutionary Synthesis of Deep Neural Networks
This work addresses efficiency for deploying deep neural networks in resource-constrained environments, representing an incremental improvement through a novel method for a known bottleneck.
The study tackled the computational complexity of deep neural networks in resource-starved scenarios by imposing synaptic precision restrictions within an evolutionary synthesis framework, resulting in a ~10X decrease in synaptic efficiency and >5X increase in inference speed for GoogLeNet-based DetectNet while preserving accuracy.
A key contributing factor to incredible success of deep neural networks has been the significant rise on massively parallel computing devices allowing researchers to greatly increase the size and depth of deep neural networks, leading to significant improvements in modeling accuracy. Although deeper, larger, or complex deep neural networks have shown considerable promise, the computational complexity of such networks is a major barrier to utilization in resource-starved scenarios. We explore the synaptogenesis of deep neural networks in the formation of efficient deep neural network architectures within an evolutionary deep intelligence framework, where a probabilistic generative modeling strategy is introduced to stochastically synthesize increasingly efficient yet effective offspring deep neural networks over generations, mimicking evolutionary processes such as heredity, random mutation, and natural selection in a probabilistic manner. In this study, we primarily explore the imposition of synaptic precision restrictions and its impact on the evolutionary synthesis of deep neural networks to synthesize more efficient network architectures tailored for resource-starved scenarios. Experimental results show significant improvements in synaptic efficiency (~10X decrease for GoogLeNet-based DetectNet) and inference speed (>5X increase for GoogLeNet-based DetectNet) while preserving modeling accuracy.