Bonnet Djohan, Hirtzlin Tifenn, Majumdar Atreya, Dalgaty Thomas, Esmanhotto Eduardo, Meli Valentina, Castellani Niccolo, Martin Simon, Nodin Jean-François, Bourgeois Guillaume, Portal Jean-Michel, Querlioz Damien, Vianello Elisa
Université Grenoble Alpes, CEA, LETI, Grenoble, France.
Université Paris-Saclay, CNRS, Centre de Nanosciences et de Nanotechnologies, Palaiseau, France.
Nat Commun. 2023 Nov 20;14(1):7530. doi: 10.1038/s41467-023-43317-9.
Safety-critical sensory applications, like medical diagnosis, demand accurate decisions from limited, noisy data. Bayesian neural networks excel at such tasks, offering predictive uncertainty assessment. However, because of their probabilistic nature, they are computationally intensive. An innovative solution utilizes memristors' inherent probabilistic nature to implement Bayesian neural networks. However, when using memristors, statistical effects follow the laws of device physics, whereas in Bayesian neural networks, those effects can take arbitrary shapes. This work overcome this difficulty by adopting a variational inference training augmented by a "technological loss", incorporating memristor physics. This technique enabled programming a Bayesian neural network on 75 crossbar arrays of 1,024 memristors, incorporating CMOS periphery for in-memory computing. The experimental neural network classified heartbeats with high accuracy, and estimated the certainty of its predictions. The results reveal orders-of-magnitude improvement in inference energy efficiency compared to a microcontroller or an embedded graphics processing unit performing the same task.
安全关键型传感应用，如医学诊断，需要从有限的噪声数据中做出准确决策。贝叶斯神经网络擅长此类任务，可提供预测不确定性评估。然而，由于其概率性质，计算量很大。一种创新解决方案利用忆阻器固有的概率性质来实现贝叶斯神经网络。但是，在使用忆阻器时，统计效应遵循器件物理规律，而在贝叶斯神经网络中，这些效应可能呈现任意形状。这项工作通过采用由“技术损失”增强的变分推理训练克服了这一困难，其中纳入了忆阻器物理特性。该技术能够在由1024个忆阻器组成的75个交叉阵列上对贝叶斯神经网络进行编程，并结合CMOS外围电路进行内存计算。实验性神经网络对心跳进行了高精度分类，并估计了其预测的确定性。结果表明，与执行相同任务的微控制器或嵌入式图形处理单元相比，推理能效提高了几个数量级。
