Implementing Spiking Neural Networks on Neuromorphic Architectures: A Review

Abstract

Recently, both industry and academia have proposed several different neuromorphic systems to execute machine learning applications that are designed using Spiking Neural Networks (SNNs). With the growing complexity on design and technology fronts, programming such systems to admit and execute a machine learning application is becoming increasingly challenging. Additionally, neuromorphic systems are required to guarantee real-time performance, consume lower energy, and provide tolerance to logic and memory failures. Consequently, there is a clear need for system software frameworks that can implement machine learning applications on current and emerging neuromorphic systems, and simultaneously address performance, energy, and reliability. Here, we provide a comprehensive overview of such frameworks proposed for both, platform-based design and hardware-software co-design. We highlight challenges and opportunities that the future holds in the area of system software technology for neuromorphic computing.

Nonvolatile Memories in Spiking Neural Network Architectures: Current and Emerging Trends

“…While traditional von Neumann architectures have one or more central processing units physically separated from the main memory, neuromorphic architectures exploit the co-localization of memory and compute, near and in-memory computation [18]. Simultaneously to the tremendous progress in devising novel neuromorphic computing architectures, there has been many recent works that address how to map and compile (trained) SNNs models for efficient execution in neuromorphic hardware [19][20][21][22][23][24][25][26][27][28][29][30][31].…”

Integrated Memristor Network for Physiological Signal Processing

“…Considering the topology implementation and the updating speed of network parameters, the most commonly used feedforward and recurrent spiking networks have gradually become the basic components of complex structures. [130][131][132] The neurons are arranged in layers in the feed-forward neural network, and each neuron is combined in a fully connected form. The spiking sequence of the input layer represents the specific task encoding, the hidden layer's spiking sequence represents the information transmission, and the output layer's spiking sequence represents the network task results.…”

Complex-Exponential-Based Bio-Inspired Neuron Model Implementation in FPGA Using Xilinx System Generator and Vivado Design Suite

“…Considerable effort has been devoted to the hardware implementation of spiking neural networks, with a particular focus on FPGA-based and Application-Specific Integrated Circuit (ASIC) systems [7,8]. The paper presented in [9] describes the implementation of a spiking neural network model on a Xilinx FPGA evaluation board, utilizing a hybrid updating algorithm that combines conventional time-stepped updating and event-driven updating techniques, while using 16-bit signed fixed-point number representation.…”