论文信息 - Architecture of a Neuroprocessor Chip for Pulse-Coded Neural Networks

Architecture of a Neuroprocessor Chip for Pulse-Coded Neural Networks

We present the architecture of a processor chip to be fabricated in digital VLSI-technology which computes the function of a configurable spiking neuron model. The chip is a submodule of the MASPINN-System (Memory Optimized Accelerator for Spiking Neural Networks). The MASPINN-System is designed as a PCI-accelerator-board for real-time simulation of very complex networks of spiking neurons in the order of 10 6 neurons. Such a performance is desirable for image processing or simulations of brain regions. Within the MASPINN-System, the neuroprocessor chip processes the essential function of a spiking neuron. It models different types of postsynaptic potentials, combines these potentials to a membrane potential and based upon a dynamic threshold, it decides on spike emission. To achieve real-time simulation of very complex spiking neural networks, the architecture emphasizes parallelization in processing and reduction of bandwidth requirements.

H. Klar | T. Schoenauer | N. Mehrtash

[1] Tim Schönauer,et al. Digital simulation of spiking neural networks , 1999 .

[2] C. Spengler,et al. Contour Segmentation with Recurrent Neural Networks of Pulse-Coding Neurons , 1997, CAIP.

[3] Christoph von der Malsburg,et al. The Correlation Theory of Brain Function , 1994 .

[4] Heinrich Klar,et al. A SIMD/dataflow architecture for a neurocomputer for spike-processing neural networks (NESPINN) , 1996, Proceedings of Fifth International Conference on Microelectronics for Neural Networks.

[5] Tim Schönauer,et al. Simulation of Spiking Neural Networks on Different Hardware Platforms , 1997, ICANN.

[6] Martin Schäfer,et al. An accelerator for neural networks with pulse-coded model neurons , 1999, IEEE Trans. Neural Networks.

[7] Jason M. Kinser,et al. Image Processing using Pulse-Coupled Neural Networks , 1998, Perspectives in Neural Computing.

[8] T. Schoenauer,et al. MASPINN: novel concepts for a neuroaccelerator for spiking neural networks , 1999, Other Conferences.