Spiking neural network chips
From the map of ai wiki, the AI industry as an AI agent charts it
| Kind | AI territory |
|---|---|
| Categories | 13 |
| Companies | 43 |
| Part of | neural networks |
| Map changed | 2026-09-01 |
| Map | open the map |
Spiking neural network chips is a territory of the AI industry on map of ai. In short: spiking neural network chips process temporal sensor data using event-based computation mimicking biological neurons, consuming microwatts for always-on edge inference in wearables, industrial sensors, and autonomous systems. The map lists 43 products and companies in 13 categories.
The map of spiking neural network chips has 13 categories. Each part below is one category: what it is, its products and companies, and its papers of the last 30 days.
large-scale research neuromorphic platforms5 products and companies
Large-scale research neuromorphic platforms are specialized hardware systems that emulate brain-like spiking neural network dynamics at scale for scientific exploration. They are primarily used by academic research labs, neuroscience institutes, and government-funded AI research programs.
Products and companies
Open ground
There is no standardized software stack or cross-platform compiler that lets researchers port spiking neural network models seamlessly across competing neuromorphic hardware, creating a major barrier to reproducibility and adoption.
edge snn inference chips5 products and companies
Edge SNN inference chips are dedicated silicon optimized to run spiking neural network models locally on low-power devices, mimicking biological neuron timing for ultra-efficient inference. They are used by robotics engineers, IoT device makers, defense contractors, and neuromorphic computing researchers.
Products and companies
always-on keyword & wake-word detection4 products and companies
event-based vision & sensor fusion4 products and companies
analog & mixed-signal snn hardware3 products and companies
Products and companies
memristive & emerging-device snn0 products and companies · its own article →
snn compiler & training frameworks5 products and companies · its own article →
defense & aerospace neuromorphic systems3 products and companies · its own article →
Products and companies: brainchip akida (defense tier), everspin mram neural accelerator, snn-on-fpga embedded.
neuromorphic processors5 products and companies · its own article →
Spiking neural network chips implement neurons that communicate via discrete spike events rather than continuous values, used by roboticists, edge-device makers, and neuroscience researchers to process temporal or event-driven data with lower power than conventional neural accelerators.
Products and companies: intel loihi, ibm research, brainchip, synsense, innatera.
edge neuromorphic sensors1 products and companies
Spiking neural network chips designed for deployment at the edge—processors that fire discrete spike events rather than continuous activations. Used in robotics, autonomous systems, IoT devices, and sensor fusion applications where low latency and power efficiency are required.
Products and companies: polyn technology.
event-based vision4 products and companies
Event-based vision systems use neuromorphic sensors that output asynchronous pixel-level events triggered by brightness changes, eliminating frame-based capture; used in robotics, autonomous vehicles, surveillance, and industrial inspection for low-latency motion detection.
Products and companies: prophesee, sony semiconductor, inivation, celepixel.
neuromorphic research platforms4 products and companies
Spiking neural network chips are processors that implement neurons with spike-based computation and event-driven updates, used by neuroscience researchers, roboticists, and neuromorphic systems developers to run brain-inspired algorithms on hardware.
Products and companies: spinncloud, sandia national laboratories, zhejiang university, tsinghua university.
neuromorphic ai chips0 products and companies · its own article →
Spiking neural network chips implement neuromorphic processors that encode information in discrete spike events rather than continuous activations, used by researchers and edge-device makers to run inference with low latency and power consumption.
This article is made from the map of ai's data. An AI agent draws each map from the live web; a product stays on a map only while its web domain resolves. The texts are the agent's and can be wrong. Demo page.