Search Results for author:
Found 13 papers, 5 papers with code
Self-Supervised Time Series Representation Learning via Cross Reconstruction Transformer
In this paper, we aim at learning representations for time series from a new perspective and propose Cross Reconstruction Transformer (CRT) to solve the aforementioned problems in a unified way.
A Deep Bayesian Neural Network for Cardiac Arrhythmia Classification with Rejection from ECG Recordings
Finally, with the help of a clinician, we conduct case studies to explain the results of large uncertainties and incorrect predictions with small uncertainties.
A Simple Self-Supervised ECG Representation Learning Method via Manipulated Temporal-Spatial Reverse Detection
To verify the effectiveness of the proposed method, we perform a downstream task to detect atrial fibrillation (AF) which is one of the most common ECG tasks.
MetaVA: Curriculum Meta-learning and Pre-fine-tuning of Deep Neural Networks for Detecting Ventricular Arrhythmias based on ECGs
MAML is expected to better transfer the knowledge from a large dataset and use only a few recordings to quickly adapt the model to a new person.
Composing Recurrent Spiking Neural Networks using Locally-Recurrent Motifs and Risk-Mitigating Architectural Optimization
The small size of the motifs and sparse inter-motif connectivity leads to an RSNN architecture scalable to large network sizes.
Backpropagated Neighborhood Aggregation for Accurate Training of Spiking Neural Networks
While backpropagation (BP) has been applied to spiking neural networks (SNNs) achieving encouraging results, a key challenge involved is to backpropagate a continuous-valued loss over layers of spiking neurons exhibiting discontinuous all-or-none firing activities.
Skip-Connected Self-Recurrent Spiking Neural Networks with Joint Intrinsic Parameter and Synaptic Weight Training
Moreover, we propose a new backpropagation (BP) method called backpropagated intrinsic plasticity (BIP) to further boost the performance of ScSr-SNNs by training intrinsic model parameters.
Temporal Spike Sequence Learning via Backpropagation for Deep Spiking Neural Networks
Spiking neural networks (SNNs) are well suited for spatio-temporal learning and implementations on energy-efficient event-driven neuromorphic processors.
Boosting Throughput and Efficiency of Hardware Spiking Neural Accelerators using Time Compression Supporting Multiple Spike Codes
Using spiking speech and image recognition datasets, we demonstrate the feasibility of supporting large time compression ratios of up to 16x, delivering up to 15. 93x, 13. 88x, and 86. 21x improvements in throughput, energy dissipation, the tradeoffs between hardware area, runtime, energy, and classification accuracy, respectively based on different spike codes on a Xilinx Zynq-7000 FPGA.
Spike-Train Level Backpropagation for Training Deep Recurrent Spiking Neural Networks
However, the practical application of RSNNs is severely limited by challenges in training.
Multiple Linear Regression Haze-removal Model Based on Dark Channel Prior
The RESIDE dataset provides enough synthetic hazy images and their corresponding groundtruth images to train and test.
Robust Deep Multi-Modal Sensor Fusion using Fusion Weight Regularization and Target Learning
Sensor fusion has wide applications in many domains including health care and autonomous systems.
Hybrid Macro/Micro Level Backpropagation for Training Deep Spiking Neural Networks
We evaluate the proposed HM2-BP algorithm by training deep fully connected and convolutional SNNs based on the static MNIST [14] and dynamic neuromorphic N-MNIST [26].
