Session

DescriptionThis session features six papers of innovative research papers focused on advancing the efficiency and performance of neural network designs. Topics cover include neural architecture search, in-sensor compression for edge applications, performance prediction for autotuning workloads, acceleration through efficient bit-serial processing, mixed-precision methods, and FPGA-based framework for neuro-symbolic AI. Together, these works highlight the transformative potential of next-generation technologies in enhancing the efficiency, speed, scalability, and effectiveness of neural network-driven systems.