While modern machine learning has transformed numerous application domains, its growing computational demands increasingly constrain scalability and efficiency, particularly on embedded and resource-limited platforms. In practice, neural networks must not only operate efficiently but also provide reliable predictions under distributional shifts or unseen data. Bayesian neural networks offer a principled framework for quantifying uncertainty, yet their computational overhead further compounds these challenges. This work advances resource-efficient and robust inference for both conventional and Bayesian neural networks through the joint pursuit of algorithmic and hardware efficiency. The former reduces computation through model compression and approximate Bayesian inference, while the latter optimizes deployment on digital accelerators and explores analog hardware, bridging algorithmic design and physical realization. The first contribution, Galen, performs automatic layer-specific compression guided by sensitivity analysis and hardware-in-the-loop feedback. Analog accelerators offer efficiency gains at the cost of noise; this work models device imperfections and extends noisy training to nonstationary conditions, improving robustness and stability. A second line of work advances probabilistic inference, developing analytic and ensemble approximations that replace costly sampling, integrate into a compiler stack, and optimize embedded inference. Finally, probabilistic photonic computing introduces a paradigm where controlled analog noise acts as an intrinsic entropy source, enabling fast, energy-efficient probabilistic inference directly in hardware. Together, these studies demonstrate how efficiency and reliability can be advanced jointly through algorithm-hardware co-design, laying the foundation for the next generation of trustworthy, energy-efficient machine-learning systems.

翻译：尽管现代机器学习已变革了众多应用领域，但其日益增长的计算需求正逐渐制约着可扩展性与效率，尤其在嵌入式与资源受限平台上。实践中，神经网络不仅需要高效运行，还必须在分布偏移或未见数据下提供可靠预测。贝叶斯神经网络为量化不确定性提供了理论框架，但其计算开销进一步加剧了这些挑战。本研究通过算法与硬件效率的协同优化，推进了传统神经网络与贝叶斯神经网络的资源高效与鲁棒推理。前者通过模型压缩与近似贝叶斯推理降低计算量，后者则优化数字加速器部署并探索模拟硬件，从而桥接算法设计与物理实现。首个贡献Galen通过敏感性分析与硬件在环反馈指导的自动层特异性压缩实现高效推理。模拟加速器以噪声为代价提升效率；本研究对器件缺陷进行建模，并将噪声训练扩展至非平稳条件，从而增强鲁棒性与稳定性。第二项工作推进概率推理，开发了替代昂贵采样的解析与集成近似方法，将其集成至编译器栈并优化嵌入式推理。最后，概率光子计算引入了一种新范式，其中受控模拟噪声作为内禀熵源，直接在硬件中实现快速、高能效的概率推理。这些研究共同表明，通过算法-硬件协同设计可同步提升效率与可靠性，为下一代可信赖、高能效机器学习系统奠定基础。