conftrace_

gradient vanishing

29 papers

Explore in graph

Co-occurring keywords

recurrent neural network (1790) spiking neural network (331) neural network optimization (1293) surrogate gradient (31) vanishing gradient (43) convolutional neural network (4226) residual network (211) layer normalization (65) long-term dependency (44) gradient propagation (34)

Papers

CREST: An Efficient Conjointly-trained Spike-driven Framework for Event-based Object Detection Exploiting Spatiotemporal Dynamics AAAI 2025
Self-Adjust Softmax EMNLP 2025
Scaling ResNets in the Large-depth Regime JMLR 2025
Adaptive Gradient Learning for Spiking Neural Networks by Exploiting Membrane Potential Dynamics IJCAI 2025
Bi-ViT: Pushing the Limit of Vision Transformer Quantization AAAI 2024
Take A Shortcut Back: Mitigating the Gradient Vanishing for Training Spiking Neural Networks NIPS 2024
B2T Connection: Serving Stability and Performance in Deep Transformers ACL 2023
Learnable Surrogate Gradient for Direct Training Spiking Neural Networks IJCAI 2023
Fast Saturating Gate for Learning Long Time Scales with Recurrent Neural Networks AAAI 2023
Training Spiking Neural Networks with Event-driven Backpropagation NIPS 2022
Multi-Level Firing with Spiking DS-ResNet: Enabling Better and Deeper Directly-Trained Spiking Neural Networks IJCAI 2022
Signal Propagation in Transformers: Theoretical Perspectives and the Role of Rank Collapse NIPS 2022
Scaling-up Diverse Orthogonal Convolutional Networks by a Paraunitary Framework ICML 2022
Improved Gradient-Based Adversarial Attacks for Quantized Networks AAAI 2022
Adversarial Attack against Cross-lingual Knowledge Graph Alignment EMNLP 2021
SBO-RNN: Reformulating Recurrent Neural Networks via Stochastic Bilevel Optimization NIPS 2021
Time Adaptive Recurrent Neural Network CVPR 2021
Temporal Pyramid Recurrent Neural Network AAAI 2020
Improving Deep Transformer with Depth-Scaled Initialization and Merged Attention IJCNLP 2019
Improving Deep Transformer with Depth-Scaled Initialization and Merged Attention EMNLP 2019
Lifted Proximal Operator Machines AAAI 2019
Backbone Cannot Be Trained at Once: Rolling Back to Pre-Trained Network for Person Re-Identification AAAI 2019
Beyond Backprop: Online Alternating Minimization with Auxiliary Variables ICML 2019
DTMT: A Novel Deep Transition Architecture for Neural Machine Translation AAAI 2019
Layer Trajectory LSTM INTERSPEECH 2018