← Back to the NeuroCore 2026 Page
The Track on Analog, Mixed‑Signal, and Memristive Neuromorphic Systems invites original research contributions that advance the design, modeling, and deployment of hardware systems inspired by biological neural computation. As the field moves toward ultra‑low‑power, high‑density, and event‑driven intelligence, analog and mixed‑signal circuits—combined with emerging memristive technologies—offer unprecedented opportunities for real‑time learning, high‑bandwidth sensing, and massively parallel neural processing. This track brings together researchers from circuits, devices, neuromorphic engineering, computer architecture, and computational neuroscience to explore innovations that push neuromorphic hardware to the next level.
We welcome submissions including, but not limited to, the following areas:
1. Analog and Mixed‑Signal Neuromorphic Circuits
- Subthreshold analog neuron and synapse circuits
- Mixed‑signal SNN processors and event‑driven compute blocks
- Low‑power, low‑latency analog front‑ends for neuromorphic sensing
- Noise‑tolerant and variability‑aware circuit techniques
- On‑chip learning engines and adaptive analog circuits
2. Memristive and Emerging‑Device Neuromorphic Systems
- Memristor‑based synapses and neurons (RRAM, PCM, FeFET, OxRAM, etc.)
- Crossbar arrays for in‑memory spiking computation
- Device‑circuit co‑design for learning rules (STDP, Hebbian, local plasticity)
- Reliability, endurance, and variability modeling for memristive SNNs
- Hybrid CMOS–memristive neuromorphic architectures
3. System‑Level Integration and Architectures
- Large‑scale analog/mixed‑signal neuromorphic processors
- 3D‑IC, chiplet, and heterogeneous integration for neuromorphic systems
- Event‑driven communication fabrics and spike‑routing architectures
- Power, thermal, and noise management in analog neuromorphic platforms
- Multi‑sensor fusion using analog and mixed‑signal neuromorphic circuits
4. Algorithms, Learning, and Co‑Design
- Algorithm–circuit co‑design for analog and memristive neuromorphic hardware
- Learning rules optimized for analog or device‑level constraints
- Calibration, compensation, and adaptation techniques
- Mapping and programming frameworks for mixed‑signal neuromorphic systems
5. Applications and Demonstrations
- Real‑time robotics, autonomous systems, and sensorimotor control
- Event‑based vision, audition, and tactile processing
- Biomedical and brain–machine interface applications
- Ultra‑low‑power edge intelligence and always‑on sensing
- Benchmarking methodologies and performance evaluation
