L'intelligence artificielle au service de la maintenance by Emmanuel Senft, May 18, Afficher plus. Modelling creative thinking with computational methods by Lonneke van der Plas, March 07, Intelligence Artificielle: calculer, est-ce penser?
Physics-based modeling and the quest for intelligent robots by Prof. Active interaction between robots and humans for automatic curriculum learning and assistive robotics by Dr. Understanding the mysteries of sleep: From brain physiology to neural networks by Olivier Pallanca, November 12, Could deep learning video generation models understand the physical world? A philosophical perspective by Pierre Beckmann, October 02, Speaker recognition in forensics and homeland security by Itshak Lapidot, September 27, Generalization vs.
Leonardi, August 23, Test-time adaptation for automatic pathological speech detection in noisy environments by Mahdi Amiri, July 16, What is that thing called Software Release Procedure? And how can it help you make history? Towards privacy-preserving data sharing with noisy embeddings by Dina El Zein, June 11, Combining digital histopathology and RNA-sequencing towards molecular understanding of cancer morphological and cellular diversity by Garance Haefliger, June 04, Daniel Attinger, June 03, A demonstrator for multi-image deconvolution of thermal images by Florian Piras, May 14, Contextualisation and text adaptation of E2E automatic speech recognition by Iuliia Nigmatulina, March 12, Generalization of radiomics features in ever-changing acquisition setups by Oscar Jimenez Biosignal Processing , February 06, Conversational Speech Translation and Recognition Recent developments in the theory of modern machine learning by David Belius, January 23, Abstract: For wireless networks, edge intelligence is hindered from revolutionising how smartphones and base stations process and analyse data by bringing AI capabilities closer to the source of data generation.
Split Learning SL will be introduced in this talk. This new distributed deep learning paradigm enables resource-constrained devices to offload substantial training workloads to edge servers via layer-wise model partitioning. By resorting to parallel training across multiple devices, SL addresses the latency and bandwidth challenges of traditional centralised and federated learning, ensuring efficient and privacy-preserving data processing at the edge of wireless networks.
I will present our recent work on Efficient Parallel Split Learning EPSL , designed to overcome the limitations of existing parallel split learning schemes. EPSL enhances model training efficiency by parallelising client-side computations and aggregating last-layer gradients, reducing server-side training and communication overhead.
