Spiking neural network – Definition & Meaning

Definition of spiking neural network

: a neural network whose units communicate through discrete events called spikes and use the timing of those spikes as part of the computation, resembling aspects of biological neural signaling
- The sensor sent sparse events directly to a spiking neural network running on neuromorphic hardware.
- Training the SNN was difficult because spike generation is not smoothly differentiable.

Origin & history

Spiking neural networks grew from computational neuroscience models that represent neurons as event-producing dynamical systems. They are often called third-generation neural networks because they add spike timing and internal state to the activation-based abstractions used by earlier artificial neural networks.

Test yourself

Which of these is the meaning of spiking neural network?

Related terms

neural network a computing system made of many simple connected units ("neurons") arranged in layers, which… deep learning a type of machine learning that uses neural networks with many layers, allowing a system to… gradient descent an optimization method that improves a model step by step by moving its parameters a little in… TinyML the field of running machine-learning models directly on extremely low-power… NPU neural processing unit: a small, power-efficient chip inside phones and laptops built to run… computer vision the field of AI that enables computers to interpret images and video, for example recognizing…

Cite this entry

"Spiking neural network." AI Dictionary, Dadgogo, https://dadgogo.com/dictionary/spiking-neural-network/. Accessed 12 Oct. 2026.