Architecture Engineers Award

The rising environmental impact of deep learning has made sustainability an essential consideration in model design. While existing sustainable Neural Architecture Search (NAS) methods primarily focus on reducing the computational cost of the search process, they often overlook the substantial emissions generated by the final architectures during training and deployment. This oversight allows carbon-intensive models to persist even after an efficient search. To address this gap, this research emphasizes the need to embed long-term emission awareness directly into NAS objectives. Limitations of Conventional Sustainable NAS Approaches Traditional sustainability efforts in NAS mainly target the efficiency of the search algorithm itself, such as reducing GPU hours or computational overhead during architecture exploration. However, these methods neglect the broader lifecycle emissions of selected models, including training, fine-tuning, and large-scale deployment. This partial optimizati...

Spiking Neural Networks (SNNs) represent a biologically inspired computing paradigm that transmits information through discrete spikes, offering improved biological interpretability and superior energy efficiency. Despite these advantages, the design of high-performance SNN architectures remains a major challenge, as existing structures rely heavily on manual engineering and expert intuition. This research addresses this issue by proposing a fully automated method to discover optimal SNN architectures using a predictor-assisted evolutionary neural architecture search framework, aiming to enhance performance while reducing computational cost and energy consumption. Limitations of Manual SNN Architecture Design Traditional approaches to SNN architecture development depend largely on manual design strategies, making them inflexible and difficult to scale. These human-crafted architectures often suffer from limited adaptability, restricted search space exploration, and reliance on expe...