Search Results for author:
Found 10 papers, 6 papers with code
Converting Artificial Neural Networks to Spiking Neural Networks via Parameter Calibration
We demonstrate that our method can handle the SNN conversion with batch normalization layers and effectively preserve the high accuracy even in 32 time steps.
Temporal Efficient Training of Spiking Neural Network via Gradient Re-weighting
Then we introduce the temporal efficient training (TET) approach to compensate for the loss of momentum in the gradient descent with SG so that the training process can converge into flatter minima with better generalizability.
Control Theory Illustrates the Energy Efficiency in the Dynamic Reconfiguration of Functional Connectivity
The brain's functional connectivity fluctuates over time instead of remaining steady in a stationary mode even during the resting state.
Multi-modal Attention Network for Stock Movements Prediction
Traditionally, the prediction of future stock movements is based on the historical trading record.
Differentiable Spike: Rethinking Gradient-Descent for Training Spiking Neural Networks
Based on the introduced finite difference gradient, we propose a new family of Differentiable Spike (Dspike) functions that can adaptively evolve during training to find the optimal shape and smoothness for gradient estimation.
Ranked #4 on
Event data classification
on CIFAR10-DVS
A Unified Framework for Generalized Low-Shot Medical Image Segmentation with Scarce Data
In this work, we propose a unified framework for generalized low-shot (one- and few-shot) medical image segmentation based on distance metric learning (DML).
A Free Lunch From ANN: Towards Efficient, Accurate Spiking Neural Networks Calibration
Moreover, our calibration algorithm can produce SNN with state-of-the-art architecture on the large-scale ImageNet dataset, including MobileNet and RegNet.
Optimal Conversion of Conventional Artificial Neural Networks to Spiking Neural Networks
As an alternative, many efforts have been devoted to converting conventional ANNs into SNNs by copying the weights from ANNs and adjusting the spiking threshold potential of neurons in SNNs.
BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction
To further employ the power of quantization, the mixed precision technique is incorporated in our framework by approximating the inter-layer and intra-layer sensitivity.
MixMix: All You Need for Data-Free Compression Are Feature and Data Mixing
However, the inversion process only utilizes biased feature statistics stored in one model and is from low-dimension to high-dimension.
