MISEL project constitutes a holistic approach consisting of the whole value chain: materials research for back-end of line (BEOL) processing-compatible densely-packed ferroelectric non-volatile memories (FeRAMs) and intensity-adaptive photodetectors, novel neuromorphic computing algorithms and circuit implementations, and system level benchmarking. The stand-alone system fabricated in MISEL will be tested on timely and challenging applications such as distinguishing birds from drones through their spatio-temporal flying signature, and scene anomaly detection from a mobile platform.
The envisioned MISEL system consists of three processing units:
- cellular sensor-processor with multi-band QD/MIG photodetector monolithically fabricated on top of silicon computing layer provides signal enhancement by on-sensing computing/adaptation, and generates complex events;
- cerebellar processor with non-volatile FeRAM monolithically fabricated on top of CMOS structures provides spatio-temporal awareness and quick reactions (reflexes);
- cortical processor with non-volatile FeRAM monolithically fabricated on top of CMOS structures takes care of higher-level analysis, spatio-temporal classification, and predictions, leading to conscious decisions.