Imagen de Portada

Advancing On-Device Neural Network Training with TinyPropv2: Dynamic, Sparse, and Efficient Backpropagation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Rüb, Marcus, Sikora, Axel, Mueller-Gritschneder, Daniel
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

A Continual and Incremental Learning Approach for TinyML On-device Training Using Dataset Distillation and Model Size Adaption
por: Rüb, Marcus, et al.
Publicado: (2024)

DRIP: DRop unImportant data Points -- Enhancing Machine Learning Efficiency with Grad-CAM-Based Real-Time Data Prioritization for On-Device Training
por: Rüb, Marcus, et al.
Publicado: (2025)

Dynamic Spectral Backpropagation for Efficient Neural Network Training
por: Muthuraman, Mannmohan
Publicado: (2025)

Dense Backpropagation Improves Training for Sparse Mixture-of-Experts
por: Panda, Ashwinee, et al.
Publicado: (2025)

Beyond Backpropagation: Exploring Innovative Algorithms for Energy-Efficient Deep Neural Network Training
por: Spyra, Przemysław
Publicado: (2025)

StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs
por: Luo, Qijun, et al.
Publicado: (2025)

MLonMCU: TinyML Benchmarking with Fast Retargeting
por: van Kempen, Philipp, et al.
Publicado: (2023)

ssProp: Energy-Efficient Training for Convolutional Neural Networks with Scheduled Sparse Back Propagation
por: Zhong, Lujia, et al.
Publicado: (2024)

Efficient On-Policy Reinforcement Learning via Exploration of Sparse Parameter Space
por: Zhang, Xinyu, et al.
Publicado: (2025)

Tiny, On-Device Decision Makers with the MiniConv Library
por: Purves, Carlos
Publicado: (2025)

SAL: Selective Adaptive Learning for Backpropagation-Free Training with Sparsification
por: Liu, Fanping, et al.
Publicado: (2026)

NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks
por: Hao, Yongchang, et al.
Publicado: (2024)

Linear Mode Connectivity in Sparse Neural Networks
por: McDermott, Luke, et al.
Publicado: (2023)

TinyGraph: Joint Feature and Node Condensation for Graph Neural Networks
por: Liu, Yezi, et al.
Publicado: (2024)

HKAN: Hierarchical Kolmogorov-Arnold Network without Backpropagation
por: Dudek, Grzegorz, et al.
Publicado: (2025)

Stochastic Layer-wise Learning: Scalable and Efficient Alternative to Backpropagation
por: Yin, Bojian, et al.
Publicado: (2025)

Backpropagation-free Spiking Neural Networks with the Forward-Forward Algorithm
por: Ghader, Mohammadnavid, et al.
Publicado: (2025)

On-Device Training of Fully Quantized Deep Neural Networks on Cortex-M Microcontrollers
por: Deutel, Mark, et al.
Publicado: (2024)

Local Pairwise Distance Matching for Backpropagation-Free Reinforcement Learning
por: Tanneberg, Daniel
Publicado: (2025)

Practical Boolean Backpropagation
por: Golbert, Simon
Publicado: (2025)

Dendron: Enhancing Human Activity Recognition with On-Device TinyML Learning
por: Shalby, Hazem Hesham Yousef, et al.
Publicado: (2025)

Efficient Federated Finetuning of Tiny Transformers with Resource-Constrained Devices
por: Pfeiffer, Kilian, et al.
Publicado: (2024)

Can LLMs Revolutionize the Design of Explainable and Efficient TinyML Models?
por: Zeinaty, Christophe El, et al.
Publicado: (2025)

Topology-Aware Revival for Efficient Sparse Training
por: Jin, Meiling, et al.
Publicado: (2026)

LeanTTA: A Backpropagation-Free and Stateless Approach to Quantized Test-Time Adaptation on Edge Devices
por: Dong, Cynthia, et al.
Publicado: (2025)

Hybrid Convolution and Vision Transformer NAS Search Space for TinyML Image Classification
por: Djajapermana, Mikhael, et al.
Publicado: (2025)

Scalable Learning in Structured Recurrent Spiking Neural Networks without Backpropagation
por: Tang, Bo, et al.
Publicado: (2026)

DTMM: Deploying TinyML Models on Extremely Weak IoT Devices with Pruning
por: Han, Lixiang, et al.
Publicado: (2024)

Agentic Neural Networks: Self-Evolving Multi-Agent Systems via Textual Backpropagation
por: Ma, Xiaowen, et al.
Publicado: (2025)

Beyond Backpropagation: Optimization with Multi-Tangent Forward Gradients
por: Flügel, Katharina, et al.
Publicado: (2024)

TinyVQA: Compact Multimodal Deep Neural Network for Visual Question Answering on Resource-Constrained Devices
por: Rashid, Hasib-Al, et al.
Publicado: (2024)

Epi$^2$-Net: Advancing Epidemic Dynamics Forecasting with Physics-Inspired Neural Networks
por: Sun, Rui, et al.
Publicado: (2025)

SparseBalance: Load-Balanced Long Context Training with Dynamic Sparse Attention
por: Xu, Hongtao, et al.
Publicado: (2026)

Sparse Decomposition of Graph Neural Networks
por: Hu, Yaochen, et al.
Publicado: (2024)

Less is More: Recursive Reasoning with Tiny Networks
por: Jolicoeur-Martineau, Alexia
Publicado: (2025)

ELM-DeepONets: Backpropagation-Free Training of Deep Operator Networks via Extreme Learning Machines
por: Son, Hwijae
Publicado: (2025)

Backpropagation-Free Multi-modal On-Device Model Adaptation via Cloud-Device Collaboration
por: Ji, Wei, et al.
Publicado: (2024)

QuadraNet V2: Efficient and Sustainable Training of High-Order Neural Networks with Quadratic Adaptation
por: Xu, Chenhui, et al.
Publicado: (2024)

BEND: Bagging Deep Learning Training Based on Efficient Neural Network Diffusion
por: Wei, Jia, et al.
Publicado: (2024)

On the Expressive Power of Graph Neural Networks
por: Nalwade, Ashwin, et al.
Publicado: (2024)