MLSP-P65.2
SPARSE AUTOENCODERS MAKE AUDIO FOUNDATION MODELS MORE EXPLAINABLE
Théo Mariotte, Martin Lebourdais, LIUM, Le Mans Université, France; Antonio Almudévar, ViVoLab, I3A, University of Zaragoza, Spain; Marie Tahon, LIUM, Le Mans Université, France; Alfonso Ortega, ViVoLab, I3A, University of Zaragoza, Spain; Nicolas Dugué, LIUM, Le Mans Université, France
Session:
MLSP-P65: Explainable Machine Learning for Signal Processing I Poster
Track:
Machine Learning for Signal Processing [ML]
Location:
Poster Area 7
Presentation Time:
Thu, 7 May, 16:30 - 18:30
Presentation
Discussion
Resources
No resources available.
Session MLSP-P65
MLSP-P65.1: TRAIN2EXPLAIN: TRAINING OPTIMIZATION FOR EXPLANATION IMPROVEMENT
Cristian Morasso, University of Verona, Italy; Tristan Groussard, University of Poitiers, France; Giorgio Dolci, Lorenza Brusini, University of Verona, Italy; Theo Biardeau, David Helbert, Christine Fernandez Maloigne, University of Poitiers, France; Gloria Menegaz, University of Verona, Italy
MLSP-P65.2: SPARSE AUTOENCODERS MAKE AUDIO FOUNDATION MODELS MORE EXPLAINABLE
Théo Mariotte, Martin Lebourdais, LIUM, Le Mans Université, France; Antonio Almudévar, ViVoLab, I3A, University of Zaragoza, Spain; Marie Tahon, LIUM, Le Mans Université, France; Alfonso Ortega, ViVoLab, I3A, University of Zaragoza, Spain; Nicolas Dugué, LIUM, Le Mans Université, France
MLSP-P65.3: Higher-Order Feature Attribution: Bridging Statistics, Explainable AI, and Topological Signal Processing
Kurt Butler, The University of Edinburgh, United Kingdom of Great Britain and Northern Ireland; Guanchao Feng, Petar Djuric, Stony Brook University, United States of America
MLSP-P65.4: SEAM-Former: Infusing Waveform Semantics into Transformers for Explainable Myocardial Infarction Localization via 12-lead ECG
Yuhang Liu, Fan Lin, Huazhong University of Science and Technology, China; QiangQ Xie, Tao Wang, Zhigang Ye, Wuhan United Imaging Surgical Co., Ltd., China; Qiang Li, Peng Zhang, Huazhong University of Science and Technology, China
MLSP-P65.5: DOES THE PRE-TRAINING OF AN EMBEDDING INFLUENCE ITS ENCODING OF AGE?
Carole Millot, Clara Ponchard, Inria, France; Jean-François Bonastre, AMIAD, France; Cédric Gendrot, Sorbonne Nouvelle, France
MLSP-P65.6: Toward Faithful Explanations in Acoustic Anomaly Detection
Maab Elrashid, Mila-Quebec AI Institute/Concordia University/Université Laval, Canada; Anthony Deschênes, Université Laval, Canada; Cem Subakan, Mila-Quebec AI Institute/Concordia University/Université Laval, Canada; Mirco Ravanelli, Mila-Quebec AI Institute/Concordia University, Canada; Rémi Georges, Michael Morin, Université Laval, Canada
MLSP-P65.7: EXTRACTING FORMULAE IN MANY-VALUED LOGIC FROM DEEP NEURAL NETWORKS
Yani Zhang, Helmut Bölcskei, ETH Zurich, Switzerland
MLSP-P65.8: G2P-Rec: Graph-to-Prompt Synergistic Reasoning for Knowledge-Enhanced Recommendation
Jiaxin Hu, Tao Wang, Hongrun Wang, Anqi Wu, Xinshuang Xu, Sun Yat-sen University, China
MLSP-P65.9: Behind the Scenes: Mechanistic Interpretability of LoRA-adapted Whisper for Speech Emotion Recognition
Yujian Ma, Xikun Lu, Jinqiu Sang, East China Normal University, China; Xianquan Jiang, Boin Hearing Technology (Shanghai) Co., LTD, China; Ruizhe Li, University of Aberdeen, United Kingdom of Great Britain and Northern Ireland
MLSP-P65.10: DYNAMIC BASIS GENERATION AND MULTI-SCALE GAUSSIAN RESPONSE FUSION FOR ROBUST POINT CLOUD REGISTRATION
Yuxin Yang, Limei Hu, Hao Yi, Feng Chen, Southwest University, China
Contacts