Options
Zapata, Mireya
PSoC-Based Real-Time Data Acquisition for a Scalable Spiking Neural Network Hardware Architecture
Real-Time Adaptive Physical Sensor Processing with SNN Hardware
2018
,
Zapata, Mireya
,
Balaji U.K.
,
Madrenas J.
Data acquisition for monitoring the spiky activity of large-scale SNN hardware architectures are a challenge due to their time constraints, complexity, large logic size, and so on. This paper presents a versatile PSoC-Based Data Acquisition prototype, where a specialized Master Device is used for this purpose. It benefits from the heterogeneous nature of SoC platforms that allows it to host programmable logic together with a hard-core ARM processor integrating memory and a variety of peripherals in a single chip. The presented design enables monitoring the performance of a multi-chip neural network through a single Ethernet interface in a hardware and software co-design, which is combined with an application developed in Python that allows the visualization on the PC of a dynamic raster plot of neural activity. In addition, an example of full platform functionality is shown. © 2018 IEEE.
2023
,
Madrenas J.
,
Vallejo-Mancero B.
,
Oltra-Oltra J.À.
,
Zapata, Mireya
,
Cosp-Vilella J.
,
Calatayud R.
,
Moriya S.
,
Sato S.
Spiking Neural Networks (SNNs) offer bioinspired computation based on local adaptation and plasticity as well as close biological compatibility. In this work, after reviewing the Hardware Emulator of Evolving Neural Systems (HEENS) architecture and its Computer-Aided Engineering (CAE) design flow, a spiking implementation of an adaptive physical sensor input scheme based on time-rate Band-Pass Filter (BPF) is proposed for real-time execution of large dynamic range sensory edge processing nodes. Simulation and experimental results of the SNN operating in real-time with an adaptive-range accelerometer input example are shown. This work opens the path to compute with SNNs multiple physical sensor information for perception applications. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.