12 datasets found

The dataset used for training and testing the accelerated ALIF SNN model.

We implemented synaptic plasticity and show that while individual weights show small deviations due to stochastic rounding, the statistics of a learning rule are preserved.

We dissect an individual computational unit from Loihi. The basic building block is a spiking unit inspired by a current based leaky integrate and fire (LIF) neuron model.

Developing intelligent neuromorphic solutions remains a challenging endeavour. It requires a solid conceptual understanding of the hardware’s fundamental building blocks. Beyond...

The anisotropic network is a spiking neural network model that generates spatially asymmetric non-plastic connections. The model is based on a biologically-inspired rule for...

The proposed approach can encode voltages with high accuracy. The dataset is a spike train generated by the proposed analog-to-spike encoder (ASE) using phase encoding.

This paper introduces Graph Reasoning Spiking Neural Networks (GRSNN) for efficient graph reasoning, leveraging the temporal domain and synaptic delay.

A minimal motif consists of only two interconnected neurons – one excitatory neuron with a delayed self-connection (autapse) and one inhibitory neuron, yielding a bistable motif...

The dataset is used to test the proposed learning mechanism for spiking neural networks.

The dataset used in this paper is a spiking neural network (SNN) with 20 layers, where each layer has 2000 LIF neurons. The input spikes are Poisson trains at a target rate of...

The proposed model is validated on a Xilinx Virtex 6 FPGA and analyzes a fully connected network which consists of 800 neurons and 12,544 synapses in real-time.

The dataset used in this paper is a spiking neural network dataset.