Search Results for author:
Found 7 papers, 3 papers with code
Scaling Supervised Local Learning with Augmented Auxiliary Networks
AugLocal constructs each hidden layer's auxiliary network by uniformly selecting a small subset of layers from its subsequent network layers to enhance their synergy.
Efficient Online Learning for Networks of Two-Compartment Spiking Neurons
The brain-inspired Spiking Neural Networks (SNNs) have garnered considerable research interest due to their superior performance and energy efficiency in processing temporal signals.
TC-LIF: A Two-Compartment Spiking Neuron Model for Long-Term Sequential Modelling
The identification of sensory cues associated with potential opportunities and dangers is frequently complicated by unrelated events that separate useful cues by long delays.
Long Short-term Memory with Two-Compartment Spiking Neuron
The identification of sensory cues associated with potential opportunities and dangers is frequently complicated by unrelated events that separate useful cues by long delays.
Deep Spike Learning with Local Classifiers
We then propose two variants that additionally incorporate temporal dependencies through a backward and forward process, respectively.
Synaptic Learning with Augmented Spikes
Traditional neuron models use analog values for information representation and computation, while all-or-nothing spikes are employed in the spiking ones.
Constructing Accurate and Efficient Deep Spiking Neural Networks with Double-threshold and Augmented Schemes
We examine the performance of our methods based on MNIST, Fashion-MNIST and CIFAR10 datasets.
