Cover Image

DNN Modularization via Activation-Driven Training

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ngo, Tuan, Hassan, Abid, Shafiq, Saad, Medvidovic, Nenad
Format:	Preprint
Published:	2024
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

DAVIS: OOD Detection via Dominant Activations and Variance for Increased Separation
by: Hassan, Abid, et al.
Published: (2026)

Catalyst: Out-of-Distribution Detection via Elastic Scaling
by: Hassan, Abid, et al.
Published: (2026)

Toward Improved Deep Learning-based Vulnerability Detection
by: Sejfia, Adriana, et al.
Published: (2024)

Are We Learning the Right Features? A Framework for Evaluating DL-Based Software Vulnerability Detection Solutions
by: Das, Satyaki, et al.
Published: (2025)

Identifying Appropriately-Sized Services with Deep Reinforcement Learning
by: Fabiha, Syeda Tasnim, et al.
Published: (2025)

NeMo: A Neuron-Level Modularizing-While-Training Approach for Decomposing DNN Models
by: Bi, Xiaohan, et al.
Published: (2025)

DAF: An Efficient End-to-End Dynamic Activation Framework for on-Device DNN Training
by: Liu, Renyuan, et al.
Published: (2025)

NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds
by: Zhao, Boran, et al.
Published: (2025)

Rethinking the Potential of Layer Freezing for Efficient DNN Training
by: Yang, Chence, et al.
Published: (2025)

Exploring Variance Reduction in Importance Sampling for Efficient DNN Training
by: Kutsuna, Takuro
Published: (2025)

DecTrain: Deciding When to Train a Monocular Depth DNN Online
by: Fu, Zih-Sing, et al.
Published: (2024)

Revisiting DNN Training for Intermittently-Powered Energy-Harvesting Micro-Computers
by: Mishra, Cyan Subhra, et al.
Published: (2024)

Optimizing DNN Inference on Multi-Accelerator SoCs at Training-time
by: Risso, Matteo, et al.
Published: (2024)

HAVER: Instance-Dependent Error Bounds for Maximum Mean Estimation and Applications to Q-Learning and Monte Carlo Tree Search
by: Nguyen, Tuan Ngo, et al.
Published: (2024)

Provable Benefits of Sinusoidal Activation for Modular Addition
by: Huang, Tianlong, et al.
Published: (2025)

Accuracy Booster: Enabling 4-bit Fixed-point Arithmetic for DNN Training
by: Harma, Simla Burcu, et al.
Published: (2022)

Spectral Embedding via Chebyshev Bases for Robust DeepONet Approximation
by: Abid, Muhammad, et al.
Published: (2025)

DNN Memory Footprint Reduction via Post-Training Intra-Layer Multi-Precision Quantization
by: Ghavami, Behnam, et al.
Published: (2024)

Exploration of Activation Fault Reliability in Quantized Systolic Array-Based DNN Accelerators
by: Taheri, Mahdi, et al.
Published: (2024)

MLTCP: Congestion Control for DNN Training
by: Rajasekaran, Sudarsanan, et al.
Published: (2024)

PaSE: Parallelization Strategies for Efficient DNN Training
by: Elango, Venmugil
Published: (2024)

Mirage: An RNS-Based Photonic Accelerator for DNN Training
by: Demirkiran, Cansu, et al.
Published: (2023)

MAED: Mathematical Activation Error Detection for Mitigating Physical Fault Attacks in DNN Inference
by: Ahmadi, Kasra, et al.
Published: (2026)

Performance Analysis of DNN Inference/Training with Convolution and non-Convolution Operations
by: Esmaeilzadeh, Hadi, et al.
Published: (2023)

AdapSNE: Adaptive Fireworks-Optimized and Entropy-Guided Dataset Sampling for Edge DNN Training
by: Zhao, Boran, et al.
Published: (2025)

Fixing the Loose Brake: Exponential-Tailed Stopping Time in Best Arm Identification
by: Balagopalan, Kapilan, et al.
Published: (2024)

DAISM: Digital Approximate In-SRAM Multiplier-based Accelerator for DNN Training and Inference
by: Sonnino, Lorenzo, et al.
Published: (2023)

Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts
by: Morrison, Jacob, et al.
Published: (2026)

Learning from Language Feedback via Variational Policy Distillation
by: Li, Yang, et al.
Published: (2026)

Clustering and Alignment: Understanding the Training Dynamics in Modular Addition
by: Musat, Tiberiu
Published: (2024)

AXLearn: Modular, Hardware-Agnostic Large Model Training
by: Lee, Mark, et al.
Published: (2025)

Energy-Aware DNN Graph Optimization
by: Wang, Yu, et al.
Published: (2020)

Enlightenment Period Improving DNN Performance
by: Liu, Tiantian, et al.
Published: (2025)

Training-Free Policy Violation Detection via Activation-Space Whitening in LLMs
by: Rachmil, Oren, et al.
Published: (2025)

MAx-DNN: Multi-Level Arithmetic Approximation for Energy-Efficient DNN Hardware Accelerators
by: Leon, Vasileios, et al.
Published: (2025)

Feather: An Elegant Solution to Effective DNN Sparsification
by: Georgoulakis, Athanasios Glentis, et al.
Published: (2023)

Towards a Flexible and High-Fidelity Approach to Distributed DNN Training Emulation
by: Liu, Banruo, et al.
Published: (2024)

Unsupervised Pairwise Causal Discovery on Heterogeneous Data using Mutual Information Measures
by: Trilla, Alexandre, et al.
Published: (2024)

Training Neural Networks for Modularity aids Interpretability
by: Golechha, Satvik, et al.
Published: (2024)

A Self-Commissioning Edge Computing Method for Data-Driven Anomaly Detection in Power Electronic Systems
by: Gomez, Pere Izquierdo, et al.
Published: (2023)