Copertina

Enhancing Interpretability Through Loss-Defined Classification Objective in Structured Latent Spaces

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Geissler, Daniel, Zhou, Bo, Liu, Mengxi, Lukowicz, Paul
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

The Power of Training: How Different Neural Network Setups Influence the Energy Demand
di: Geißler, Daniel, et al.
Pubblicazione: (2024)

CoSS: Co-optimizing Sensor and Sampling Rate for Data-Efficient AI in Human Activity Recognition
di: Liu, Mengxi, et al.
Pubblicazione: (2024)

Human in the Latent Loop (HILL): Interactively Guiding Model Training Through Human Intuition
di: Geissler, Daniel, et al.
Pubblicazione: (2025)

iKAN: Global Incremental Learning with KAN for Human Activity Recognition Across Heterogeneous Datasets
di: Liu, Mengxi, et al.
Pubblicazione: (2024)

Towards certifiable AI in aviation: landscape, challenges, and opportunities
di: Bello, Hymalai, et al.
Pubblicazione: (2024)

Bridging Generalization and Personalization in Human Activity Recognition via On-Device Few-Shot Learning
di: Kang, Pixi, et al.
Pubblicazione: (2025)

ALS-HAR: Harnessing Wearable Ambient Light Sensors to Enhance IMU-based Human Activity Recogntion
di: Ray, Lala Shakti Swarup, et al.
Pubblicazione: (2024)

iMove: Exploring Bio-impedance Sensing for Fitness Activity Recognition
di: Liu, Mengxi, et al.
Pubblicazione: (2024)

Misinforming LLMs: vulnerabilities, challenges and opportunities
di: Zhou, Bo, et al.
Pubblicazione: (2024)

Leveraging Hybrid Intelligence Towards Sustainable and Energy-Efficient Machine Learning
di: Geissler, Daniel, et al.
Pubblicazione: (2024)

Initial Investigation of Kolmogorov-Arnold Networks (KANs) as Feature Extractors for IMU Based Human Activity Recognition
di: Liu, Mengxi, et al.
Pubblicazione: (2024)

Spend More to Save More (SM2): An Energy-Aware Implementation of Successive Halving for Sustainable Hyperparameter Optimization
di: Geissler, Daniel, et al.
Pubblicazione: (2024)

DPCformer: An Interpretable Deep Learning Model for Genomic Prediction in Crops
di: Deng, Pengcheng, et al.
Pubblicazione: (2025)

Closed-Form Interpretation of Neural Network Latent Spaces with Symbolic Gradients
di: Wetzel, Sebastian J., et al.
Pubblicazione: (2024)

Decoding Latent Spaces: Assessing the Interpretability of Time Series Foundation Models for Visual Analytics
di: Santamaria-Valenzuela, Inmaculada, et al.
Pubblicazione: (2025)

TinierHAR: Towards Ultra-Lightweight Deep Learning Models for Efficient Human Activity Recognition on Edge Devices
di: Bian, Sizhen, et al.
Pubblicazione: (2025)

Towards Interpreting Multi-Objective Feature Associations
di: Pillai, Nisha, et al.
Pubblicazione: (2024)

Enhancing Uncertainty Estimation and Interpretability via Bayesian Non-negative Decision Layer
di: Hu, Xinyue, et al.
Pubblicazione: (2025)

Exploring Criteria of Loss Reweighting to Enhance LLM Unlearning
di: Yang, Puning, et al.
Pubblicazione: (2025)

CR-LSO: Convex Neural Architecture Optimization in the Latent Space of Graph Variational Autoencoder with Input Convex Neural Networks
di: Rao, Xuan, et al.
Pubblicazione: (2022)

Interpretability by Design for Efficient Multi-Objective Reinforcement Learning
di: Xia, Qiyue, et al.
Pubblicazione: (2025)

Soft Contextualized Encoder For User Defined Text Classification
di: Maheshwari, Charu, et al.
Pubblicazione: (2026)

In Search for Architectures and Loss Functions in Multi-Objective Reinforcement Learning
di: Terekhov, Mikhail, et al.
Pubblicazione: (2024)

Multi-Objective Loss Balancing for Physics-Informed Deep Learning
di: Bischof, Rafael, et al.
Pubblicazione: (2021)

Certified Robustness from Approximate Gaussian Mixture Structures in Pretrained Latent Spaces
di: Emmanouilidis, Konstantinos, et al.
Pubblicazione: (2026)

A Latent Space Metric for Enhancing Prediction Confidence in Earth Observation Data
di: Pitsiorlas, Ioannis, et al.
Pubblicazione: (2024)

EIDOS: Latent-Space Predictive Learning for Time Series Foundation Models
di: Zhou, Xinxing, et al.
Pubblicazione: (2026)

Rethinking Independent Cross-Entropy Loss For Graph-Structured Data
di: Miao, Rui, et al.
Pubblicazione: (2024)

Searching Latent Program Spaces
di: Macfarlane, Matthew V, et al.
Pubblicazione: (2024)

Enhancing Interpretability in Generative AI Through Search-Based Data Influence Analysis
di: Aivalis, Theodoros, et al.
Pubblicazione: (2025)

Characterizing Continuous and Discrete Hybrid Latent Spaces for Structural Connectomes
di: Rudravaram, Gaurav, et al.
Pubblicazione: (2025)

In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering
di: Liu, Sheng, et al.
Pubblicazione: (2023)

KAN-MLP-Mixer: A comprehensive investigation of the usage of Kolmogorov-Arnold Networks (KANs) for improving IMU-based Human Activity Recognition
di: Liu, Mengxi, et al.
Pubblicazione: (2026)

Learning Interpretable Rules for Scalable Data Representation and Classification
di: Wang, Zhuo, et al.
Pubblicazione: (2023)

Enhanced Importance Sampling through Latent Space Exploration in Normalizing Flows
di: Kruse, Liam A., et al.
Pubblicazione: (2025)

Latent Diffusion : Multi-Dimension Stable Diffusion Latent Space Explorer
di: Zhong, Zhihua, et al.
Pubblicazione: (2025)

Explanation Space: A New Perspective into Time Series Interpretability
di: Rezaei, Shahbaz, et al.
Pubblicazione: (2024)

Age Predictors Through the Lens of Generalization, Bias Mitigation, and Interpretability: Reflections on Causal Implications
di: Paul, Debdas, et al.
Pubblicazione: (2026)

LDMol: A Text-to-Molecule Diffusion Model with Structurally Informative Latent Space Surpasses AR Models
di: Chang, Jinho, et al.
Pubblicazione: (2024)

Benchmarking Counterfactual Interpretability in Deep Learning Models for Time Series Classification
di: Kan, Ziwen, et al.
Pubblicazione: (2024)