Papers Efficient Neural Network
“Efficient Neural Network” 태그가 달린 논문 224편 · 필터 해제
Interact2Vec -- An efficient neural network-based model for simultaneously learning users and items embeddings in recommender systems
Over the past decade, recommender systems have experienced a surge in popularity. Despite notable progress, they grapple with challenging issues, such as high data dimensionality and sparseness. Representing users and it…
Efficient Neural NetworkRecommendation SystemsLinearity-based neural network compression
In neural network compression, most current methods reduce unnecessary parameters by measuring importance and redundancy. To augment already highly optimized existing solutions, we propose linearity-based compression as …
Efficient Neural NetworkNeural Network CompressionAccelerating 3D Gaussian Splatting with Neural Sorting and Axis-Oriented Rasterization
3D Gaussian Splatting (3DGS) has recently gained significant attention for high-quality and efficient view synthesis, making it widely adopted in fields such as AR/VR, robotics, and autonomous driving. Despite its impres…
3DGSAutonomous DrivingEfficient Neural NetworkSpikePingpong: High-Frequency Spike Vision-based Robot Learning for Precise Striking in Table Tennis Game
Learning to control high-speed objects in the real world remains a challenging frontier in robotics. Table tennis serves as an ideal testbed for this problem, demanding both rapid interception of fast-moving balls and pr…
Efficient Neural NetworkFrictionImitation LearningDynamic Spectral Backpropagation for Efficient Neural Network Training
Dynamic Spectral Backpropagation (DSBP) enhances neural network training under resource constraints by projecting gradients onto principal eigenvectors, reducing complexity and promoting flat minima. Five extensions are …
Efficient Neural NetworkMeta-LearningProbabilistic Emulation of the Community Radiative Transfer Model Using Machine Learning
The continuous improvement in weather forecast skill over the past several decades is largely due to the increasing quantity of available satellite observations and their assimilation into operational forecast systems. A…
Computational EfficiencyEfficient Neural NetworkCan LLMs Revolutionize the Design of Explainable and Efficient TinyML Models?
This paper introduces a novel framework for designing efficient neural network architectures specifically tailored to tiny machine learning (TinyML) platforms. By leveraging large language models (LLMs) for neural archit…
Computational EfficiencyEfficient Neural NetworkKnowledge DistillationNeural Architecture SearchLightSNN: Lightweight Architecture Search for Sparse and Accurate Spiking Neural Networks
Spiking Neural Networks (SNNs) are highly regarded for their energy efficiency, inherent activation sparsity, and suitability for real-time processing in edge devices. However, most current SNN methods adopt architecture…
Efficient Neural NetworkEfficient Reachability Analysis for Convolutional Neural Networks Using Hybrid Zonotopes
Feedforward neural networks are widely used in autonomous systems, particularly for control and perception tasks within the system loop. However, their vulnerability to adversarial attacks necessitates formal verificatio…
Efficient Neural NetworkReinforcement Learning-based Threat Assessment
In some game scenarios, due to the uncertainty of the number of enemy units and the priority of various attributes, the evaluation of the threat level of enemy units as well as the screening has been a challenging resear…
AttributeEfficient Neural Networkreinforcement-learningReinforcement LearningAutomatic Joint Structured Pruning and Quantization for Efficient Neural Network Training and Compression
Structured pruning and quantization are fundamental techniques used to reduce the size of deep neural networks (DNNs) and typically are applied independently. Applying these techniques jointly via co-optimization has the…
Efficient Neural NetworkQuantizationWhen do they StOP?: A First Step Towards Automatically Identifying Team Communication in the Operating Room
Purpose: Surgical performance depends not only on surgeons' technical skills but also on team communication within and across the different professional groups present during the operation. Therefore, automatically ident…
Action DetectionActivity DetectionEfficient Neural NetworkHarmonic Loss Trains Interpretable AI Models
In this paper, we introduce **harmonic loss** as an alternative to the standard cross-entropy loss for training neural networks and large language models (LLMs). Harmonic loss enables improved interpretability and faster…
Efficient Neural NetworkMultiscale Training of Convolutional Neural Networks
Convolutional Neural Networks (CNNs) are the backbone of many deep learning methods, but optimizing them remains computationally expensive. To address this, we explore multiscale training frameworks and mathematically id…
Efficient Neural NetworkMono-Forward: Backpropagation-Free Algorithm for Efficient Neural Network Training Harnessing Local Errors
Backpropagation is the standard method for achieving state-of-the-art accuracy in neural network training, but it often imposes high memory costs and lacks biological plausibility. In this paper, we introduce the Mono-Fo…
Efficient Neural NetworkHALO: Hadamard-Assisted Lower-Precision Optimization for LLMs
Quantized training of Large Language Models (LLMs) remains an open challenge, as maintaining accuracy while performing all matrix multiplications in low precision has proven difficult. This is particularly the case when …
Efficient Neural Networkparameter-efficient fine-tuningQuantizationLearn2Mix: Training Neural Networks Using Adaptive Data Integration
Accelerating model convergence in resource-constrained environments is essential for fast and efficient neural network training. This work presents learn2mix, a new training strategy that adaptively adjusts class proport…
Data IntegrationEfficient Neural NetworkEfficient Neural Network Encoding for 3D Color Lookup Tables
3D color lookup tables (LUTs) enable precise color manipulation by mapping input RGB values to specific output RGB values. 3D LUTs are instrumental in various applications, including video editing, in-camera processing, …
Color ManipulationEfficient Neural NetworkVideo EditingA Digital twin for Diesel Engines: Operator-infused PINNs with Transfer Learning for Engine Health Monitoring
Improving diesel engine efficiency and emission reduction have been critical research topics. Recent government regulations have shifted this focus to another important area related to engine health and performance monit…
Efficient Neural NetworkTransfer LearningPrediction-Enhanced Monte Carlo: A Machine Learning View on Control Variate
For many complex simulation tasks spanning areas such as healthcare, engineering, and finance, Monte Carlo (MC) methods are invaluable due to their unbiased estimates and precise error quantification. Nevertheless, Monte…
Efficient Neural NetworkPrediction