Skip to Main content Skip to Navigation
Conference papers

DiagnoseNET: Automatic Framework to Scale Neural Networks on Heterogeneous Systems Applied to Medical Diagnosis

John García 1 Frédéric Precioso 2, 3 Pascal Staccini 4 Michel Riveill 1, 3
2 Laboratoire d'Informatique, Signaux, et Systèmes de Sophia-Antipolis (I3S) / Equipe KEIA
Laboratoire I3S - SPARKS - Scalable and Pervasive softwARe and Knowledge Systems
3 MAASAI - Modèles et algorithmes pour l’intelligence artificielle
CRISAM - Inria Sophia Antipolis - Méditerranée , Laboratoire I3S - SPARKS - Scalable and Pervasive softwARe and Knowledge Systems, UNS - Université Nice Sophia Antipolis (... - 2019), JAD - Laboratoire Jean Alexandre Dieudonné
Abstract : Determine an optimal generalization model with deep neu-ral networks for a medical task is an expensive process that generally requires large amounts of data and computing power. Furthermore, scale deep learning workflows over a wide range of emerging heterogeneous system architecture increases the programming expressiveness complexity for model training and the computing orchestration. We introduce Diag-noseNET, a programming framework designed for scaling deep learning models over heterogeneous systems applied to medical diagnosis. It is designed as a modular framework to enable the deep learning workflow management and allows the expressiveness of neural networks written in TensorFlow, while its runtime abstracts the data locality, micro batch-ing and the distributed orchestration to scale the neural network model from a GPU workstation to multi-nodes. The main approach is composed through a set of gradient computation modes to adapt the neural network according to the memory capacity, the workers' number, the coordination method and the communication protocol (GRPC or MPI) for achieving a balance between accuracy and energy consumption. The experiments carried out allow to evaluate the computational performance in terms of accuracy, convergence time and worker scalability to determine an optimal neural architecture over a mini-cluster of Jetson TX2 nodes. These experiments were performed using two medical cases of study, the former dataset is composed by clinical descriptors collected during the first week of hospitalization of patients in the Provence-Alpes-Côte d'Azur region; the second dataset uses a short ECG records between 30 and 60 seconds, obtained as part of the PhysioNet 2017 Challenge.
Complete list of metadatas

Cited literature [15 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02869960
Contributor : Michel Riveill <>
Submitted on : Tuesday, June 16, 2020 - 1:37:08 PM
Last modification on : Monday, June 22, 2020 - 10:45:22 AM

File

2020-08-ICITCS-DiagnoseNET- Au...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02869960, version 1

Collections

Citation

John García, Frédéric Precioso, Pascal Staccini, Michel Riveill. DiagnoseNET: Automatic Framework to Scale Neural Networks on Heterogeneous Systems Applied to Medical Diagnosis. 8th International Conference on IT Convergence and Security 2020, Aug 2020, Nha Trang, Vietnam. ⟨hal-02869960⟩

Share

Metrics

Record views

21

Files downloads

32