Meo / Silvestri Machine Learning and Principles and Practice of Knowledge Discovery in Databases

International Workshops of ECML PKDD 2023, Turin, Italy, September 18–22, 2023, Revised Selected Papers, Part V
Erscheinungsjahr 2025
ISBN: 978-3-031-74643-7
Verlag: Springer International Publishing
Format: PDF
Kopierschutz: 1 - PDF Watermark

E-Book, Englisch, Band 2137, 488 Seiten, eBook

Reihe: Communications in Computer and Information Science

The five-volume set CCIS 2133-2137 constitutes the refereed proceedings of the workshops held in conjunction with the Joint European Conference on Machine Learning and Knowledge Discovery in Databases, ECML PKDD 2023, which took place in Turin, Italy, during September 18-22, 2023.The 200 full papers presented in these proceedings were carefully reviewed and selected from 515 submissions. The papers have been organized in the following tracks:Part I: Advances in Interpretable Machine Learning and Artificial Intelligence -- Joint Workshop and Tutorial; BIAS 2023 - 3rd Workshop on Bias and Fairness in AI; Biased Data in Conversational Agents; Explainable Artificial Intelligence: From Static to Dynamic; ML, Law and Society; Part II: RKDE 2023: 1st International Tutorial and Workshop on Responsible Knowledge Discovery in Education; SoGood 2023 – 8th Workshop on Data Science for Social Good; Towards Hybrid Human-Machine Learning and Decision Making (HLDM); Uncertainty meets explainability in machine learning; Workshop: Deep Learning and Multimedia Forensics. Combating fake media and misinformation; Part III: XAI-TS: Explainable AI for Time Series: Advances and Applications; XKDD 2023: 5th International Workshop on eXplainable Knowledge Discovery in Data Mining; Deep Learning for Sustainable Precision Agriculture; Knowledge Guided Machine Learning; MACLEAN: MAChine Learning for EArth ObservatioN; MLG: Mining and Learning with Graphs; Neuro Explicit AI and Expert Informed ML for Engineering and Physical Sciences; New Frontiers in Mining Complex Patterns; Part IV: PharML, Machine Learning for Pharma and Healthcare Applications; Simplification, Compression, Efficiency and Frugality for Artificial intelligence; Workshop on Uplift Modeling and Causal Machine Learning for Operational Decision Making; 6th Workshop on AI in Aging, Rehabilitation and Intelligent Assisted Living (ARIAL); Adapting to Change: Reliable Multimodal Learning Across Domains; AI4M: AI for Manufacturing; Part V: Challenges and Opportunities of Large Language Models in Real-World Machine Learning Applications; Deep learning meets Neuromorphic Hardware; Discovery challenge; ITEM: IoT, Edge, and Mobile for Embedded Machine Learning; LIMBO - LearnIng and Mining for BlOckchains; Machine Learning for Cybersecurity (MLCS 2023); MIDAS - The 8th Workshop on MIning DAta for financial applicationS; Workshop on Advancements in Federated Learning.

Zielgruppe

Research

Autoren/Hrsg.

Meo, Rosa

Silvestri, Fabrizio

Inhaltsverzeichnis

.- Challenges and Opportunities of Large Language Models in Real-World Machine Learning Applications..- Contextual Data Augmentation for Task-Oriented Dialog Systems..- Fairness of ChatGPT and the Role Of Explainable-Guided Prompts..- Deep learning meets Neuromorphic Hardware..- Non-Dissipative Propagation by Randomized Anti-Symmetric Deep Graph Networks..- On the Noise Robustness of Analog Complex-Valued Neural Networks..- Neu-BrAuER: a neuromorphic Braille letters audio-reader for commercial edge devices..- Discovery challenge..- Transductive Fire-affected Area Segmentation with False-Color Data..- Post Wildfire Burnt-up Detection using Siamese UNet..- Predicting Exoplanetary Features with a Residual Model for Uniform and Gaussian Distributions..- Reproducing Bayesian Posterior Distributions for Exoplanet Atmospheric Parameter Retrievals with a Machine Learning Surrogate Model..- Simulation-based Inference for Exoplanet Atmospheric Retrieval: Insights from winning the Ariel Data Challenge 2023 using Normalizing Flows..- ITEM: IoT, Edge, and Mobile for Embedded Machine Learning..- Implications of Noise in Resistive Memory on Deep Neural Networks for Image Classification..- Evaluating custom-precision operator support in MLIR for ARM CPUs..- microYOLO: Towards Single-Shot Object Detection on Microcontrollers..- OptiSim: A Hardware-Aware Optimization Space Exploration Tool for CNN Architectures..- On the Non-Associativity of Analog Computations..- Quantized dynamics models for hardware-efficient control and planning in model-based RL..- LIMBO - LearnIng and Mining for BlOckchains..- Temporal and Geographical Analysis of Real Economic Activities in the Bitcoin Blockchain..- Machine Learning for Cybersecurity (MLCS 2023)..- A source separation approach to temporal graph modelling for computer networks..- Quantum Machine Learning for Malware Classification..- Side-channel Based Intrusion Detection for Network Equipment..- I See Dead People: Gray-Box Adversarial Attack on Image-To-Text Models..- Concept Drift Detection using Ensemble of Integrally Private Models..- MIDAS - The 8th Workshop on MIning DAta for financial applicationS..- ViBERTgrid BiLSTM-CRF: Multimodal Key Information Extraction from Unstructured Financial Documents..- Comparing Deep RL and Traditional Financial Portfolio Methods  - Full paper..- Occupational Fraud Detection through Agent-based Data Generation..- Stock Price Time Series Forecasting Using Dynamic Graph Neural Networks and Attention Mechanism in Recurrent Neural Networks..- Flexible Tails for Normalising Flows, with Application to the Modelling of Financial Return Data..- Exploring Alternative Data for Nowcasting: A Case Study on US GDP using Topic Attention..- Topology-Agnostic Detection of Temporal Money Laundering Flows in Billion-Scale Transactions..- Boosting Credit Risk Data Quality using Machine Learning and eXplainable AI Techniques..- Ensemble methods for Stock Market Prediction..- Workshop on Advancements in Federated Learning..- Federated Learning with Neural Graphical Models..- On improving accuracy in Federated Learning using GANs-based pre-training and Ensemble Learning..- Re-evaluating the Privacy Benefit of Federated Learning..- Parameterizing Federated Continual Learning for Reproducible Research.