Jibin Wu

TL;DR: The SOM-SNN framework is shown to be highly robust to corrupting noise after multi-condition training, whereby the model is trained with noise-corrupted sound samples, and the early decision making capability of the proposed framework is discovered: an accurate classification can be made with an only partial presentation of the input.

TL;DR: This work uses SNNs for acoustic modeling and evaluates their performance on several large vocabulary recognition scenarios, demonstrating competitive ASR accuracies to their ANN counterparts while require only 10 algorithmic time steps and as low as 0.68 times total synaptic operations to classify each audio frame.

TL;DR: The contribution of spike timing dynamics to information encoding, synaptic plasticity and decision making is investigated, providing a new perspective to design of future DeepSNNs and neuromorphic hardware systems.

TL;DR: The proposed tandem learning rule offers a novel solution to training efficient, low latency, and high-accuracy deep SNNs with low computing resources and demonstrates competitive pattern recognition and regression capabilities on both the conventional frame- and event-based vision datasets.

TL;DR: This work proposes a biologically plausible speech recognition mechanism using unsupervised self-organizing map (SOM) for feature representation and event-driven spiking neural network (SNN) for spatiotemporal pattern classification that can be implemented using the artificial silicon cochlear and neuromorphic processor.