Search Results for author:
Found 4 papers, 3 papers with code
Neuromorphic Intermediate Representation: A Unified Instruction Set for Interoperable Brain-Inspired Computing
Despite a well-established mathematical foundation for neural dynamics, the implementation details vary greatly across different platforms.
Gradient-descent hardware-aware training and deployment for mixed-signal Neuromorphic processors
Here we demonstrate a novel methodology for ofDine training and deployment of spiking neural networks (SNNs) to the mixed-signal neuromorphic processor DYNAP-SE2.
Network insensitivity to parameter noise via adversarial regularization
We present a new adversarial network optimisation algorithm that attacks network parameters during training, and promotes robust performance during inference in the face of parameter variation.
Supervised training of spiking neural networks for robust deployment on mixed-signal neuromorphic processors
Our method provides robust deployment of pre-trained networks on mixed-signal neuromorphic hardware, without requiring per-device training or calibration.
