software or accelerator
Conventional ANN
Valid claim: Performs the declared tensor computation under its numeric and timing model.
Bounded substrate comparison
Artificial and spiking neural networks
When is a spike-based model meaningfully different from a conventional neural network?
Evidence status
Cites 1 source, none of which has been read
The source is named, but it has been retrieved and read as part of building this page. Nothing here has been matched to a passage, so the citations show where a reader might look rather than what was checked.
Rely on this page for
Orientation: how the topic is organised, which terms matter, and where to start reading.
Do not rely on it for
A claim you intend to act on or repeat. Follow the cited material yourself first.
event-based dynamical model
Spiking neural network
Valid claim: Performs the declared state-and-event computation under its neuron and coding model.
Comparable axes
- Same task and data split
- Matched quality constraint
- Full inference latency and resources
Non-equivalences
- A spike is not automatically a biological action potential.
- Operation counts are architecture-specific.
Comparison procedure
- 1.Freeze task and quality.
- 2.Document conversion or training.
- 3.Measure complete pipelines.
Prohibited inference
Do not infer biological realism, intelligence, or efficiency from the presence of spikes without matched task evidence and complete resource accounting.
Connected concepts and sources
- NeuroBench: Advancing Neuromorphic Computing Through Collaborative, Fair and Representative Benchmarking · National Institute of Standards and Technology
Direct answer
- When is a spike-based model meaningfully different from a conventional neural network?
Mechanism and method
- Freeze task and quality.
- Document conversion or training.
- Measure complete pipelines.
What is measured
- Same task and data split
- Matched quality constraint
- Full inference latency and resources
Comparison: Artificial and spiking neural networks
- A spike is not automatically a biological action potential.
- Operation counts are architecture-specific.
- Must not be read as: Do not infer biological realism, intelligence, or efficiency from the presence of spikes without matched task evidence and complete resource accounting.
Limitations
- A spike is not automatically a biological action potential.
- Operation counts are architecture-specific.
What this does not establish
- Do not infer biological realism, intelligence, or efficiency from the presence of spikes without matched task evidence and complete resource accounting.