Deliverables M6

D1.1 Task modeling from user definition results

D3.1 Carbon footprint-based model optimization tool 

D7.1 Data Management Plan

D7.2 Report on communication exploitation and dissemination

Deliverables M12

D2.1 Hardware Accelerator Architecture v1.0 - Summary

D4.1 Exploring new ML models report v2.0 - Summary

D5-1-Framework architecture back end front end design and release - Summary

D77 Annual report on collaboration - Summary

Scientific Publications

A Knowledge Distillation Framework for Multi-Organ Segmentation of Medaka Fish in Tomographic Image

Authors: Jwalin Bhatt, Yaroslav Zharov, Sungho Suh, Tilo Baumbach, Vincent Heuveline, and Paul Lukowicz

Efficient Self-Supervision using Patch-based Contrastive Learning for Histopathology Image Segmentation

Authors: Nicklas Boserup, Raghavendra Selvan

Addressing Sustainable ML Life-cycles through Human-Centered Design

Authors: Eya Ben Chaaben, Janin Koch

Latent Inspector: An Interactive Tool for Probing Neural Network Behaviors Through Arbitrary Latent Activation

Authors: Daniel Geißler, Bo Zhou, Paul Lukowicz

FieldHAR: A Fully Integrated End-to-end RTL Framework for Human Activity Recognition with Neural Networks from Heterogeneous Sensors

Authors: Mengxi Liu; Bo Zhou; Zimin Zhao; Hyeonseok Hong; Hyun Kim; Sungho Suh; Vitor Fortes Rey; Paul Lukowicz

Energy Efficiency Impact of Processing in Memory: A Comprehensive Review of Workloads on the UPMEM Architecture

Authors: Yann Falevoz & Julien Legriel

Novel Adaptive Quantization Methodology for 8-bit Floating-Point DNN Training

Authors: Mohammad Hassani Sadi, Chirag Sudarshan, and Norbert Wehn