Braindrop: A Mixed-Signal Neuromorphic Architecture With a Dynamical Systems-Based Programming Model
Braindrop: A Mixed-Signal Neuromorphic Architecture With a Dynamical Systems-Based Programming Model
复制标题
DOI：
10.1109/jproc.2018.2881432
复制
发表时间：
2019-01-01
影响因子：
20.6
通讯作者：
Boahen, Kwabena
中科院分区：
文献类型：
--
作者：
Neckar, Alexander;Fok, Sam;Boahen, Kwabena
Braindrop是第一个被设计成在高抽象层次上编程的神经形态系统。以前的神经形态系统是在神经突触水平上编程的，需要硬件的专业知识才能使用。与之形成鲜明对比的是，Braindrop的计算被指定为耦合的非线性动力系统，并通过自动程序合成到硬件中。该过程不仅利用Braindrop的亚阈值模拟电路结构作为动态计算原语，而且还在网络级补偿其不匹配和温度敏感的响应。因此，向用户呈现了清晰的抽象。Braindrop采用28 nm FDSOI工艺制造，在0.65 mm（2）内集成了4096个神经元。两项创新-通过模拟空间卷积进行稀疏编码和通过数字累积细化进行加权尖峰速率求和-大幅削减数字流量，将Braindrop每次等效突触操作消耗的能量降低到典型网络配置的381 fJ。
Braindrop is the first neuromorphic system designed to be programmed at a high level of abstraction. Previous neuromorphic systems were programmed at the neurosynaptic level and required expert knowledge of the hardware to use. In stark contrast, Braindrop's computations are specified as coupled nonlinear dynamical systems and synthesized to the hardware by an automated procedure. This procedure not only leverages Braindrop's fabric of subthreshold analog circuits as dynamic computational primitives but also compensates for their mismatched and temperature-sensitive responses at the network level. Thus,a clean abstraction is presented to the user. Fabricated in a 28-nm FDSOI process, Braindrop integrates 4096 neurons in 0.65 mm(2). Two innovations-sparse encoding through analog spatial convolution and weighted spike-rate summation though digital accumulative thinning-cut digital traffic drastically, reducing the energy Braindrop consumes per equivalent synaptic operation to 381 fJ for typical network configurations.