Do more with less.
Our technology brings common sense to the processing of sensor data, freeing machines to do more with less.
Accurately. Elegantly. Meaningfully.
We call this Essential AI.
BrainChip AkidaTM IP
is like no other…
Distributed computation and event-based action
delivers unparalleled performance and efficiency.
- Ultra-low latency
- Runs multiple networks simultaneously
- Performs one-shot learning
- Remarkably power efficient
- Cloud independent
- Flexible and quick to deploy
- Privacy enabling
- Good for the planet
Tech Foundations
Distributed Computation
Each NPU has dedicated compute and
memory, reducing data movement.
Event-Based Processing
NPUs perform computationally on
events (non-zero values).
Event-Based Communication
Send events over mesh network without
host CPU intermediation.
Event-Based Learning
On-Chip learning algorithm.
Akida is Uniquely Essential
BrainChip’s IP fabric can be placed either in a parallelized manner that would be ideal for ultimate performance, or space-optimized in order to reduce silicon utilization and further reduce power consumption.
Entire neural networks can be placed into the fabric, removing the need to swap weights in and out of DRAM resulting in a reduction of power consumption while increasing throughput.
Additionally, users can modify clock frequency to optimize performance and power consumption further.
