An Investigation on Spiking Neural Networks Based on the Izhikevich Neuronal Model: Spiking Processing and Hardware Approach

Abstract

The main required organ of the biological system is the Central Nervous System (CNS), which can influence the other basic organs in the human body. The basic elements of this important organ are neurons, synapses, and glias (such as astrocytes, which are the highest percentage of glias in the human brain). Investigating, modeling, simulation, and hardware implementation (realization) of different parts of the CNS are important in case of achieving a comprehensive neuronal system that is capable of emulating all aspects of the real nervous system. This paper uses a basic neuron model called the Izhikevich neuronal model to achieve a high copy of the primary nervous block, which is capable of regenerating the behaviors of the human brain. The proposed approach can regenerate all aspects of the Izhikevich neuron in high similarity degree and performances. The new model is based on Look-Up Table (LUT) modeling of the mathematical neuromorphic systems, which can be realized in a high degree of correlation with the original model. The proposed procedure is considered in three cases: 100 points LUT modeling, 1000 points LUT modeling, and 10,000 points LUT modeling. Indeed, by removing the high-cost functions in the original model, the presented model can be implemented in a low-error, high-speed, and low-area resources state in comparison with the original system. To test and validate the proposed final hardware, a digital FPGA board (Xilinx Virtex-II FPGA board) is used. Digital hardware synthesis illustrates that our presented approach can follow the Izhikevich neuron in a high-speed state (more than the original model), increase efficiency, and also reduce overhead costs. Implementation results show the overall saving of 84.30% in FPGA and also the higher frequency of the proposed model of about 264 MHz, which is significantly higher than the original model, 28 MHz.

An Optimization on the Neuronal Networks Based on the ADEX Biological Model in Terms of LUT-State Behaviors: Digital Design and Realization on FPGA Platforms

“…Interaction between these basic organs in the brain corresponds to transferring data, memory and learning [ 11 , 12 , 13 , 14 ]. In this approach, the important and basic block is neurons with a large number of connections.…”

“…The basic signal behaviors of the biological neurons are modeled by these mathematical equations. In neuron modeling, two approaches are selected: first, the models which are based on the biological neurons behavior, such as Hodgkin-Huxley (HH) [ 2 ] or the ADEX neuron model [ 5 , 6 , 7 , 8 ], and the second is based on spike state modeling, such as Izhikevich [ 3 , 4 , 11 , 12 ].…”

“…The advantage of digital approach is its flexible attributes, time-down in processing and power supply. Using reconfigurable digital boards, such as FPGAs cause the speed-up and flexibility in this case [ 8 , 9 , 10 , 11 , 12 ]. In the field of neural networks implementation, digital approach may be a suitable procedure [ 1 , 3 , 4 , 5 , 6 , 7 , 8 ].…”

“…Indeed, because of high-speed switching in the neuronal networks, it is required to have a accelerate hardware, which is capable of regenerating the same behavior and performance of the human neuronal cells. Different approaches are considered for implementing the neural networks in hardware state in the literature [ 10 , 11 , 12 , 13 , 14 ]. In the field of neuronal realization, since we have high-frequency networks, the digital way is a better solution.…”

Correction: Alkabaa et al. An Investigation on Spiking Neural Networks Based on the Izhikevich Neuronal Model: Spiking Processing and Hardware Approach. Mathematics 2022, 10, 612

“…There was an error in the original paper [1]. A paragraph including unexplained references was copied by mistake from one of the author's theses to the Introduction section.…”