Develops MHE-based training for ReLU FNNs via local observability of the weight dynamics and persistently exciting input design, with convergence guarantees for two-layer cases.
hub
Imagenet classification with deep convolutional neural networks
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
hub tools
representative citing papers
Rather than discarding non-shared features, pooling random forest trees and resolving missing splits at inference time improves swarm learning under partial feature overlap.
A mixture-of-experts hybrid quantum model achieves 0.793 average precision on credit card fraud detection compared to 0.770 for XGBoost, with modest extra inference time.
S3, an optimizer with a p-th order momentum denominator, equal EMA coefficients, and Nesterov acceleration, is claimed to match AdamW's 100k-step perplexity at 50k steps while avoiding loss spikes.
Multi-frame early fusion with single-frame supervision improves YOLOv7-tiny detection on MOT20Det and a new BOAT360 fisheye dataset.
The paper introduces CoCaR for joint submodel caching and request routing with dynamic DNNs in MEC, reporting 46% higher average inference precision in simulations and at least 32.3% QoE gain for its online variant.
A CNN plus 10-qubit variational quantum classifier reaches 99.80% accuracy on the DHCD Devanagari digit subset, though the quantum benefit is confounded by a large classical projection layer.
A survey that frames acoustic signals as physical information for world models and reviews PINNs, generative models, and self-supervised learning toward that end.
A literature survey that proposes a multi-level component taxonomy for deep-learning video super-resolution models and catalogs reported methods, datasets, and benchmarks.
ROS 2 navigation stack on Unitree Go2 Edu quadruped using RTAB-Map SLAM, AMCL/EKF localization, and Nav2 planning achieves 100/96/88% success in static/low/high dynamic library scenes with 3.7 cm map error.
citing papers explorer
-
Local Observability and Moving Horizon Estimation-based Training of Feedforward Neural Networks
Develops MHE-based training for ReLU FNNs via local observability of the weight dynamics and persistently exciting input design, with convergence guarantees for two-layer cases.
-
Mind the Missing Split: Resolving Feature Heterogeneity in Swarm Learning with Random Forests
Rather than discarding non-shared features, pooling random forest trees and resolving missing splits at inference time improves swarm learning under partial feature overlap.
-
A Mixture-of-Experts Framework for Practical Hybrid-Quantum Models in Credit Card Fraud Detection
A mixture-of-experts hybrid quantum model achieves 0.793 average precision on credit card fraud detection compared to 0.770 for XGBoost, with modest extra inference time.
-
SoftSignSGD(S3): An Enhanced Optimizer for Practical DNN Training and Loss Spikes Minimization Beyond Adam
S3, an optimizer with a p-th order momentum denominator, equal EMA coefficients, and Nesterov acceleration, is claimed to match AdamW's 100k-step perplexity at 50k steps while avoiding loss spikes.
-
Lightweight Multi-Frame Integration for Robust YOLO Object Detection in Videos
Multi-frame early fusion with single-frame supervision improves YOLOv7-tiny detection on MOT20Det and a new BOAT360 fisheye dataset.
-
Joint Optimization of DNN Model Caching and Request Routing in Mobile Edge Computing
The paper introduces CoCaR for joint submodel caching and request routing with dynamic DNNs in MEC, reporting 46% higher average inference precision in simulations and at least 32.3% QoE gain for its online variant.
-
Devanagari Digit Recognition using Quantum Machine Learning
A CNN plus 10-qubit variational quantum classifier reaches 99.80% accuracy on the DHCD Devanagari digit subset, though the quantum benefit is confounded by a large classical projection layer.
-
A Survey on World Models Grounded in Acoustic Physical Information
A survey that frames acoustic signals as physical information for world models and reviews PINNs, generative models, and self-supervised learning toward that end.
-
A Survey of Deep Learning Video Super-Resolution
A literature survey that proposes a multi-level component taxonomy for deep-learning video super-resolution models and catalogs reported methods, datasets, and benchmarks.
-
Autonomous Navigation System for Library Service Robot Based on Unitree Go2 Edu
ROS 2 navigation stack on Unitree Go2 Edu quadruped using RTAB-Map SLAM, AMCL/EKF localization, and Nav2 planning achieves 100/96/88% success in static/low/high dynamic library scenes with 3.7 cm map error.