Progressive tandem learning for pattern recognition with deep spiking neural networks
Spiking neural networks (SNNs) have shown clear advantages over traditional artificial
neural networks (ANNs) for low latency and high computational efficiency, due to their event …
neural networks (ANNs) for low latency and high computational efficiency, due to their event …
Improved robustness of reinforcement learning policies upon conversion to spiking neuronal network platforms applied to Atari Breakout game
Abstract Deep Reinforcement Learning (RL) demonstrates excellent performance on tasks
that can be solved by trained policy. It plays a dominant role among cutting-edge machine …
that can be solved by trained policy. It plays a dominant role among cutting-edge machine …
[HTML][HTML] Es-imagenet: A million event-stream classification dataset for spiking neural networks
With event-driven algorithms, especially spiking neural networks (SNNs), achieving
continuous improvement in neuromorphic vision processing, a more challenging event …
continuous improvement in neuromorphic vision processing, a more challenging event …
A spiking neural network architecture for visual motion estimation
G Orchard, R Benosman… - … Circuits and Systems …, 2013 - ieeexplore.ieee.org
Current interest in neuromorphic computing continues to drive development of sensors and
hardware for spike-based computation. Here we describe a hierarchical architecture for …
hardware for spike-based computation. Here we describe a hierarchical architecture for …
Event-based incremental broad learning system for object classification
S Gao, G Guo, CL Philip Chen - Proceedings of the IEEE …, 2019 - openaccess.thecvf.com
Event cameras are bio-inspired vision sensors that output pixel-level brightness changes
instead of RGB values. Thousands of convolutional neural networks have emerged to …
instead of RGB values. Thousands of convolutional neural networks have emerged to …
Hybrid neural network, an efficient low-power digital hardware implementation of event-based artificial neural network
Interest in event-based vision sensors has proliferated in recent years, with innovative
technology becoming more accessible to new researchers and highlighting such sensors' …
technology becoming more accessible to new researchers and highlighting such sensors' …
Unsupervised feature learning for event data: Direct vs inverse problem formulation
D Kostadinov, D Scaramuzza - 2020 25th International …, 2021 - ieeexplore.ieee.org
Event-based cameras record an asynchronous stream of per-pixel brightness changes. As
such, they have numerous advantages over the standard frame-based cameras, including …
such, they have numerous advantages over the standard frame-based cameras, including …
Algorithmic enablers for compact neural network topology hardware design: Review and trends
W Guicquero, A Verdant - 2020 IEEE International Symposium …, 2020 - ieeexplore.ieee.org
This paper reports the main State-Of-The-Art algorithmic enablers for compact Neural
Network topology design, while relying on basic numerical experiments. Embedding …
Network topology design, while relying on basic numerical experiments. Embedding …
A Shallow Spiking Neural Network for P300 Classification
K Wang, DH Zhai, S Xu - 2021 China Automation Congress …, 2021 - ieeexplore.ieee.org
P300 is widely used in brain-computer interface (BCI) systems due to its high bit rates. Fast
and accurate classification of P300 is the key to ensure the performance of P300-based …
and accurate classification of P300 is the key to ensure the performance of P300-based …