Supervised Learning in All FeFET-Based Spiking Neural Network: Opportunities and Challenges
Supervised Learning in All FeFET-Based Spiking Neural Network: Opportunities and Challenges
复制标题
DOI：
10.3389/fnins.2020.00634
复制
发表时间：
2020-06-24
影响因子：
4.3
通讯作者：
Datta, Suman
中科院分区：
文献类型：
--
作者：
Dutta, Sourav;Schafer, Clemens;Datta, Suman
人工智能（AI）的两种可能途径-（i）面向神经科学的神经形态计算[如尖峰神经网络（SNN）]和（ii）计算机科学驱动的机器学习（如深度学习）在其基本形式和编码方案方面存在很大差异（Pei等人，2019年）。与依赖具有静态非线性的神经元模型的传统深度学习方法不同，SNN试图捕获类似大脑的特征，如使用尖峰的计算。这有望提高计算平台的能源效率。为了实现更高的面积和能源效率相比，今天的硬件实现的SNN，我们需要超越传统的路线依赖于基于CMOS的数字或混合信号的神经元电路和分离的计算和存储器下的冯诺依曼架构。最近，铁电场效应晶体管（FeFET）正在探索作为一个有前途的替代构建神经形态硬件，利用其非易失性和丰富的极化切换动力学。在这项工作中，我们提出了一个全FeFET的SNN硬件，允许低功耗的尖峰为基础的信息处理和共同本地化的内存和计算（又名。内存计算）。我们实验证明了在28 nm高K金属栅FeFET技术的基本神经元和突触动力学。此外，从优化成本函数以调整突触权重的传统机器学习方法中汲取灵感，我们在SNN平台上实现了代理梯度（SG）学习算法，该算法允许我们对MNIST数据集进行监督学习。因此，我们提供了一种构建节能神经形态硬件的途径，可以支持传统的机器学习算法。最后，我们进行协同设备算法的协同设计，占设备级的变化（随机性）和有限的位精度的芯片上的突触权重（可用的模拟状态）的分类精度的影响。
The two possible pathways toward artificial intelligence (AI)-(i) neuroscience-oriented neuromorphic computing [like spiking neural network (SNN)] and (ii) computer science driven machine learning (like deep learning) differ widely in their fundamental formalism and coding schemes (Pei et al., 2019). Deviating from traditional deep learning approach of relying on neuronal models with static nonlinearities, SNNs attempt to capture brain-like features like computation using spikes. This holds the promise of improving the energy efficiency of the computing platforms. In order to achieve a much higher areal and energy efficiency compared to today's hardware implementation of SNN, we need to go beyond the traditional route of relying on CMOS-based digital or mixed-signal neuronal circuits and segregation of computation and memory under the von Neumann architecture. Recently, ferroelectric field-effect transistors (FeFETs) are being explored as a promising alternative for building neuromorphic hardware by utilizing their non-volatile nature and rich polarization switching dynamics. In this work, we propose an all FeFET-based SNN hardware that allows low-power spike-based information processing and co-localized memory and computing (a.k.a. in-memory computing). We experimentally demonstrate the essential neuronal and synaptic dynamics in a 28 nm high-K metal gate FeFET technology. Furthermore, drawing inspiration from the traditional machine learning approach of optimizing a cost function to adjust the synaptic weights, we implement a surrogate gradient (SG) learning algorithm on our SNN platform that allows us to perform supervised learning on MNIST dataset. As such, we provide a pathway toward building energy-efficient neuromorphic hardware that can support traditional machine learning algorithms. Finally, we undertake synergistic device-algorithm co-design by accounting for the impacts of device-level variation (stochasticity) and limited bit precision of on-chip synaptic weights (available analog states) on the classification accuracy.