Dynamic learning on the chip. Real-time addition of new categories. Built-in excitation/inhibition.
Recognize patterns in micro-seconds regardless of the number of models stored in the neurons.
>100K recognitions per second at 27Mhz. Less than 300 milliWatts per 1000 neurons.
Available on ASICs, SOCs, and FPGAs and can be evaluated on a variety of platforms
Digital neurons inspired by biology
- Behave collectively as a KNN (K-Nearest Neighbor) or RBF classifier (Radial Basis Function).
- All interconnected and working in parallel following a Winner-Takes-All collective behavior
- Recognize and learn a pattern in a constant time regardless of the number of neurons committed in the chip
- Cope with ill-defined and fuzzy data, high variability of context and novelty detection.
- Multiple NeuroMem chips can be daisy-chained to scale a network from 1000s to millions of neurons with the same speed and simplicity of operation as a single chip.