Deep Learning Classifier

Deep learning classifiers are artificial neural networks designed to categorize data into predefined classes, aiming for high accuracy and robustness. Current research emphasizes improving classifier reliability through techniques like novel fault detection, exploring alternative loss functions (e.g., replacing cross-entropy), and enhancing explainability via methods such as Grad-CAM and its variants. These advancements are crucial for building trustworthy AI systems across diverse applications, from medical image analysis and spam detection to spectrum sharing in next-generation communication networks, where robust and interpretable classification is paramount.

Papers

March 26, 2024

Image-based Novel Fault Detection with Deep Learning Classifiers using Hierarchical Labels
Nurettin Sergin, Jiayu Huang, Tzyy-Shuh Chang, Hao Yan
Fault Detection Deep Learning Classifier Hierarchical Label

November 27, 2023

Cross Entropy in Deep Learning of Classifiers Is Unnecessary -- ISBE Error is All You Need
Wladyslaw Skarbek
Deep Learning Back Propagation Simple Classifier Softmax Function Error Feedback Cross Entropy Deep Learning Classifier

October 12, 2023

Emergence of Latent Binary Encoding in Deep Neural Network Classifiers
Luigi Sbailò, Luca Ghiringhelli
Loss Function Latent Space Latent Representation Latent Variable Path Breaking Emergence Binary Code Deep Learning Classifier

September 22, 2023

Classification of Alzheimers Disease with Deep Learning on Eye-tracking Data
Harshinee Sriram, Cristina Conati, Thalia Field
Deep Learning Classification Code Alzheimer'S Disease Eye Tracking Data Deep Learning Classifier

August 8, 2023

Comprehensive Assessment of the Performance of Deep Learning Classifiers Reveals a Surprising Lack of Robustness
Michael W. Spratling
Native Robustness System Performance Comprehensive Evaluation Robustness Evaluation Robust Evaluation Deep Learning Classifier Benchmark Score Robust Machine Learning Lack Thereof State of the Art Robustness

July 10, 2023

False Sense of Security: Leveraging XAI to Analyze the Reasoning and True Performance of Context-less DGA Classifiers
Arthur Drichel, Ulrike Meyer
Data Detection Complex Reasoning Explainable AI xAI Community Security Related False Sense Deep Learning Classifier Botnet Related Malware Domain Generation Algorithm

June 10, 2023

Two-Stage Holistic and Contrastive Explanation of Image Classification
Weiyan Xie, Xiao-Hui Li, Zhi Lin, Leonard K. M. Poon, Caleb Chen Cao, Nevin L. Zhang
Image Classification Contrastive Explanation Deep Learning Classifier Two Stage Approach Contrastive Demonstration Explanation Output

May 18, 2023

Uncertainty Quantification in Deep Neural Networks through Statistical Inference on Latent Space
Luigi Sbailò, Luca M. Ghiringhelli
Deep Neural Network Latent Space Uncertainty Quantification Distribution Data Statistical Inference Latent Space Representation Deep Learning Classifier Overconfidence Problem

January 18, 2023

Exemplars and Counterexemplars Explanations for Image Classifiers, Targeting Skin Lesion Labeling
Carlo Metta, Riccardo Guidotti, Yuan Yin, Patrick Gallinari, Salvatore Rinzivillo
Explainable AI Line by Line Explanation Image Classifier Exemplar Image Automatic Diagnosis Deep Learning Classifier Counter Example Lesion Image

January 17, 2023

Preserving Privacy in Surgical Video Analysis Using Artificial Intelligence: A Deep Learning Classifier to Identify Out-of-Body Scenes in Endoscopic Videos
Joël L. Lavanchy, Armine Vardazaryan, Pietro Mascagni, AI4SafeChole Consortium, Didier Mutter, Nicolas Padoy
Indoor Wall Frame Installation Surgical Video Privacy Enhancing Technology Deep Learning Classifier Surgical Datasets Endoscopic Video

December 29, 2022

Problem-Dependent Power of Quantum Neural Networks on Multi-Class Classification
Yuxuan Du, Yibo Yang, Dacheng Tao, Min-Hsiu Hsieh
Convolutional Neural Network Quantum Physic Quantum Neural Network Multi Class Classification Deep Learning Classifier Quantum Memory Optimal Power

December 27, 2022

Sensing-Throughput Tradeoffs with Generative Adversarial Networks for NextG Spectrum Sharing
Yi Shi, Yalin E. Sagduyu
Generative Adversarial Network Gaussian Noise Deep Learning Classifier Spectrum Sharing Sensing Performance Human Autonomy Coexistence

December 1, 2022

GMM-IL: Image Classification using Incrementally Learnt, Independent Probabilistic Models for Small Sample Sizes
Penny Johnston, Keiller Nogueira, Kevin Swingler
Image Classification Gaussian Mixture Model Training Image Deep Learning Classifier Class Representation Small Sample Independent Model

November 3, 2022

Spam Review Detection Using Deep Learning
G. M. Shahariar, Swapnil Biswas, Faiza Omar, Faisal Muhammad Shah, Samiha Binte Hassan
Deep Learning Deep Learning Classifier Fake Review Spam Review

September 30, 2022

Evaluation of importance estimators in deep learning classifiers for Computed Tomography
Lennart Brocki, Wistan Marchadour, Jonas Maison, Bogdan Badic, Panagiotis Papadimitroulas, Mathieu Hatt, Franck Vermet, Neo Christopher Chung
Global Evaluation Inherent Interpretability Deep Convolutional Neural Network Saliency Map Computed Tomography Deep Learning Classifier Importance Estimation

July 6, 2022

A Hybrid Approach for Binary Classification of Imbalanced Data
Hsin-Han Tsai, Ta-Wei Yang, Wai-Man Wong, Cheng-Fu Chou
Ensemble Learning Binary Classification Imbalanced Data Hybrid Approach Deep Learning Classifier Imbalanced Dataset

May 22, 2022

Grad-CAM++ is Equivalent to Grad-CAM With Positive Gradients
Miguel Lerma, Mirtha Lucas
Grad CAM Deep Learning Classifier Extra Gradient

May 17, 2022

Deep Neural Network Classifier for Multi-dimensional Functional Data
Shuoyang Wang, Guanqun Cao, Zuofeng Shang
Deep Learning Classifier Functional Principal Component Functional Deep Neural Network Functional Data

March 2, 2022

Benchmarking Robustness of Deep Learning Classifiers Using Two-Factor Perturbation
Wei Dai, Daniel Berleant
Native Robustness Adversarial Image Additive Perturbation Deep Learning Classifier Robustness Benchmark Adversarial Corruption Image Perturbation

February 10, 2022

Feasible Low-thrust Trajectory Identification via a Deep Neural Network Classifier
Ruida Xie, Andrew G. Dempster
Trajectory Optimization Deep Learning Classifier Thrust Estimation Low Thrust Transfer Low Thrust Trajectory

Deep Learning Classifier

Papers

Image-based Novel Fault Detection with Deep Learning Classifiers using Hierarchical Labels

Cross Entropy in Deep Learning of Classifiers Is Unnecessary -- ISBE Error is All You Need

Emergence of Latent Binary Encoding in Deep Neural Network Classifiers

Classification of Alzheimers Disease with Deep Learning on Eye-tracking Data

Comprehensive Assessment of the Performance of Deep Learning Classifiers Reveals a Surprising Lack of Robustness

False Sense of Security: Leveraging XAI to Analyze the Reasoning and True Performance of Context-less DGA Classifiers

Two-Stage Holistic and Contrastive Explanation of Image Classification

Uncertainty Quantification in Deep Neural Networks through Statistical Inference on Latent Space

Exemplars and Counterexemplars Explanations for Image Classifiers, Targeting Skin Lesion Labeling

Preserving Privacy in Surgical Video Analysis Using Artificial Intelligence: A Deep Learning Classifier to Identify Out-of-Body Scenes in Endoscopic Videos

Problem-Dependent Power of Quantum Neural Networks on Multi-Class Classification

Sensing-Throughput Tradeoffs with Generative Adversarial Networks for NextG Spectrum Sharing

GMM-IL: Image Classification using Incrementally Learnt, Independent Probabilistic Models for Small Sample Sizes

Spam Review Detection Using Deep Learning

Evaluation of importance estimators in deep learning classifiers for Computed Tomography

A Hybrid Approach for Binary Classification of Imbalanced Data

Grad-CAM++ is Equivalent to Grad-CAM With Positive Gradients

Deep Neural Network Classifier for Multi-dimensional Functional Data

Benchmarking Robustness of Deep Learning Classifiers Using Two-Factor Perturbation

Feasible Low-thrust Trajectory Identification via a Deep Neural Network Classifier