5 papers
STEMS: Spatial-Temporal Mapping For Spiking Neural Networks
Sherif Eissa, Sander Stuijk, Floran De Putter +3
Spiking Neural Networks (SNNs) are promising bio-inspired third-generation neural networks. Recent research has trained deep SNN models with accuracy on par with Artificial Neural…
Sparse Convolutional Recurrent Learning for Efficient Event-based Neuromorphic Object Detection
Shenqi Wang, Yingfu Xu, Amirreza Yousefzadeh +4
Leveraging the high temporal resolution and dynamic range, object detection with event cameras can enhance the performance and safety of automotive and robotics applications in rea…
Efficient Synaptic Delay Implementation in Digital Event-Driven AI Accelerators
Roy Meijer, Paul Detterer, Amirreza Yousefzadeh +8
Synaptic delay parameterization of neural network models have remained largely unexplored but recent literature has been showing promising results, suggesting the delay parameteriz…
Hardware-In-The-Loop Training of a 4f Optical Correlator with Logarithmic Complexity Reduction for CNNs
Lorenzo Pes, Maryam Dehbashizadeh Chehreghan, Rick Luiken +3
This work evaluates a forward-only learning algorithm on the MNIST dataset with hardware-in-the-loop training of a 4f optical correlator, achieving 87.6% accuracy with O(n2) comple…
Hardware-aware training of models with synaptic delays for digital event-driven neuromorphic processors
Alberto Patino-Saucedo, Roy Meijer, Amirreza Yousefzadeh +6
Configurable synaptic delays are a basic feature in many neuromorphic neural network hardware accelerators. However, they have been rarely used in model implementations, despite th…