Cover Image

Dynamically Weighted Momentum with Adaptive Step Sizes for Efficient Deep Network Training

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Zhifeng, Li, Longlong, Zeng, Chunyan
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Neural and Evolutionary Computing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Bio-Inspired Adaptive Neurons for Dynamic Weighting in Artificial Neural Networks
by: Islam, Ashhadul, et al.
Published: (2024)

Advancing Training Efficiency of Deep Spiking Neural Networks through Rate-based Backpropagation
by: Yu, Chengting, et al.
Published: (2024)

Linearly Constrained Weights: Reducing Activation Shift for Faster Training of Neural Networks
by: Kutsuna, Takuro
Published: (2024)

Biologically Plausible Training of Deep Neural Networks Using a Top-down Credit Assignment Network
by: Chen, Jian-Hui, et al.
Published: (2022)

A Self-Ensemble Inspired Approach for Effective Training of Binary-Weight Spiking Neural Networks
by: Meng, Qingyan, et al.
Published: (2025)

Exploiting Chaotic Dynamics as Deep Neural Networks
by: Liu, Shuhong, et al.
Published: (2024)

APALU: A Trainable, Adaptive Activation Function for Deep Learning Networks
by: Subramanian, Barathi, et al.
Published: (2024)

Learning to Forget: Continual Learning with Adaptive Weight Decay
by: Ramesh, Aditya A., et al.
Published: (2026)

MDN: Parallelizing Stepwise Momentum for Delta Linear Attention
by: Huang, Yulong, et al.
Published: (2026)

Gated Recurrent Neural Networks with Weighted Time-Delay Feedback
by: Erichson, N. Benjamin, et al.
Published: (2022)

Bullet Trains: Parallelizing Training of Temporally Precise Spiking Neural Networks
by: Morrill, Todd, et al.
Published: (2026)

Should Under-parameterized Student Networks Copy or Average Teacher Weights?
by: Şimşek, Berfin, et al.
Published: (2023)

1D-CapsNet-LSTM: A Deep Learning-Based Model for Multi-Step Stock Index Forecasting
by: Zhang, Cheng, et al.
Published: (2023)

Efficient Deep Spiking Multi-Layer Perceptrons with Multiplication-Free Inference
by: Li, Boyan, et al.
Published: (2023)

Spiking Brain Compression: Post-Training Second-order Compression for Spiking Neural Networks
by: Shi, Lianfeng, et al.
Published: (2025)

Generalising E-prop to Deep Networks
by: Millidge, Beren
Published: (2025)

Deep Pulse-Coupled Neural Networks
by: Yi, Zexiang, et al.
Published: (2023)

SpikeVoice: High-Quality Text-to-Speech Via Efficient Spiking Neural Network
by: Wang, Kexin, et al.
Published: (2024)

Sharpness Aware Surrogate Training for Spiking Neural Networks
by: Nicholson, Maximilian
Published: (2026)

A Self-organizing Interval Type-2 Fuzzy Neural Network for Multi-Step Time Series Prediction
by: Yao, Fulong, et al.
Published: (2024)

A Backpropagation-Free Feedback-Hebbian Network for Continual Learning Dynamics
by: Li, Josh, et al.
Published: (2026)

No One-Size-Fits-All Neurons: Task-based Neurons for Artificial Neural Networks
by: Fan, Feng-Lei, et al.
Published: (2024)

Mitigating the Stability-Plasticity Dilemma in Adaptive Train Scheduling with Curriculum-Driven Continual DQN Expansion
by: Jaziri, Achref, et al.
Published: (2024)

Training Deep Boltzmann Networks with Sparse Ising Machines
by: Niazi, Shaila, et al.
Published: (2023)

SQUAT: Stateful Quantization-Aware Training in Recurrent Spiking Neural Networks
by: Venkatesh, Sreyes, et al.
Published: (2024)

Deep Intrinsic Surprise-Regularized Control (DISRC): A Biologically Inspired Mechanism for Efficient Deep Q-Learning in Sparse Environments
by: Kini, Yash, et al.
Published: (2026)

Lean and Mean Adaptive Optimization via Subset-Norm and Subspace-Momentum with Convergence Guarantees
by: Nguyen, Thien Hang, et al.
Published: (2024)

A Neural Network Training Method Based on Neuron Connection Coefficient Adjustments
by: Jiang, Kun
Published: (2025)

Training a General Spiking Neural Network with Improved Efficiency and Minimum Latency
by: Yao, Yunpeng, et al.
Published: (2024)

Time Shifts to Reduce the Size of Reservoir Computers
by: Carroll, Thomas L., et al.
Published: (2022)

A Learn-to-Optimize Approach for Coordinate-Wise Step Sizes for Quasi-Newton Methods
by: Lin, Wei, et al.
Published: (2024)

Self-Supervised Neural Architecture Search for Multimodal Deep Neural Networks
by: Suzuki, Shota, et al.
Published: (2025)

SAGRAD: A Program for Neural Network Training with Simulated Annealing and the Conjugate Gradient Method
by: Bernal, Javier, et al.
Published: (2025)

Self-Motivated Growing Neural Network for Adaptive Architecture via Local Structural Plasticity
by: Jia, Yiyang, et al.
Published: (2025)

Neuromorphic Graph Anomaly Detection via Adaptive STDP and Spiking Graph Neural Networks
by: Fofanah, Abdul Joseph, et al.
Published: (2026)

Recursive Dynamics in Fast-Weights Homeostatic Reentry Networks: Toward Reflective Intelligence
by: Chae, B. G.
Published: (2025)

Dynamic Dimension Wrapping (DDW) Algorithm: A Novel Approach for Efficient Cross-Dimensional Search in Dynamic Multidimensional Spaces
by: Jin, Dongnan, et al.
Published: (2024)

Efficient Online Learning with Predictive Coding Networks: Exploiting Temporal Correlations
by: Zadeh-Jousdani, Darius Masoum, et al.
Published: (2025)

Kernel Ridge Regression for Efficient Learning of High-Capacity Hopfield Networks
by: Tamamori, Akira
Published: (2025)

Recurrent Complex-Weighted Autoencoders for Unsupervised Object Discovery
by: Gopalakrishnan, Anand, et al.
Published: (2024)