Brain Sciences Journal (Impact Factor 3.33)
Neuromorphic computing was inspired by the biological neural networks in the human brain. Neural architectures for neuromorphic computing can be made area-efficient with memristive devices and networks. Developing efficient hardware for learning and inference tasks is important for neural computing applications. Emerging devices used for building memristive systems often suffer from variability issues, making their implementation challenging.The focus of this Special Issue is on the emerging devices, algorithms and systems that were inspired by the biological neural networks in the brain. Papers covering the latest research findings and reviews that highlight hardware implementations in memristors and neural computing, in-memory computing and neural networks, near-sensor neural networks, analog neural networks and sensor fusion, chaotic circuits and stochastic neural networks, cognitive architectures and their hardware implementations, neural circuits and ASIC, FPGA-based neural networks, hierarchal temporal networks, cellular neural networks and spiking neural networks are particularly sought after. Submissions should provide experimental evidence and results focusing on energy-efficient implementations of bio-inspired neural networks. Works that focus on algorithms need to at least cover embedded hardware or FPGA implementation. Works that detail the circuit or device level designs are also welcome if the energy and area efficiencies are reported.
Prof. Dr. Alex P James
Prof. Dr. Bhaskar Choubey
Dr. Alon Ascoli