This paper proposes ApproxiMorph, a comprehensive framework for both software and hardware co-design, targeting energy-efficient AI applications using 3D-IC-based neuromorphic systems. By leveraging parallel interconnections and high-bandwidth communications inherent to 3D-ICs, and the noise-resilience characteristics of spiking neural networks (SNNs), ApproxiMorph achieves significant power savings by exploiting (1) approximate implementation of neuron cells, (2) layer-wise approximation of SNNs through the heuristic exploration algorithm, (3) reduced-voltage operation in the 3D-stacked SRAM, and (4) incorporating a weight-tuning method. As a result, to search for the energy-optimal layer-wise approximation, ApproxiMorph explores only 0.44—0.67% of all possible combinations, achieving a 28.06% power saving for additions with a 0.60% accuracy loss in comparison to the baseline SNN for MNIST. In the VGG16 for CIFAR-10, ApproxiMorph searches around 103 combinations from over 1017 possible solutions, resulting in a 29.16% power saving with slight accuracy gain. Furthermore, integrating all methods enhances the accuracy of approximate implementations and demonstrates higher error resilience than accurate implementations.

In supply chain, catastrophic disasters such as earthquakes may prevent procurements from suppliers, which causes losses in retailers. Decentralizing orders and urgent stocks can reduce the losses, but cost the retailer. And, the losses by the catastrophic disasters are uncertain. In order to support planning of decentralizing orders and urgent stocks, we propose the evaluation method of procurement risks that are Conditional Value at Risk (CVaR) of the losses, which are often applied for a rare event causing a heavy loss. Because the uncertain procurement risk is reduced in return for the cost, the proposed method evaluates the decentralizing orders with the urgent stock based on real option approach.