Memory-efficient deep learning inference with incremental weight loading and data layout reorganization on edge systems

2021 ◽  
pp. 102183
Author(s):  
Cheng Ji ◽  
Fan Wu ◽  
Zongwei Zhu ◽  
Li-pin Chang ◽  
Huanghe Liu ◽  
...  
Keyword(s):  
Deep Learning ◽  
Data Layout ◽  
Memory Efficient ◽  
Weight Loading

scholarly journals Memory-Efficient Deep Learning on a SpiNNaker 2 Prototype

2018 ◽  
Vol 12 ◽  
Author(s):  
Chen Liu ◽  
Guillaume Bellec ◽  
Bernhard Vogginger ◽  
David Kappel ◽  
Johannes Partzsch ◽  
...  
Keyword(s):  
Deep Learning ◽  
Memory Efficient

scholarly journals Memory-Efficient Deep Learning Inference in Trusted Execution Environments

2021 ◽  
Author(s):  
Jean-Baptiste Truong ◽  
William Gallagher ◽  
Tian Guo ◽  
Robert J. Walls
Keyword(s):  
Deep Learning ◽  
Memory Efficient

Deep learning applied to seismic attribute computation

2019 ◽  
Vol 7 (3) ◽  
pp. SE141-SE150
Author(s):  
Donald P. Griffith ◽  
S. Ahmad Zamanian ◽  
Jeremy Vila ◽  
Antoine Vial-Aussavy ◽  
John Solum ◽  
...  
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Networks ◽  
Seismic Attributes ◽  
Deep Convolutional Neural Networks ◽  
Seismic Attribute ◽  
Seismic Surveys ◽  
Order Of Magnitude ◽  
User Guidance ◽  
Memory Efficient

We have trained deep convolutional neural networks (DCNs) to accelerate the computation of seismic attributes by an order of magnitude. These results are enabled by overcoming the prohibitive memory requirements typical of 3D DCNs for segmentation and regression by implementing a novel, memory-efficient 3D-to-2D convolutional architecture and by including tens of thousands of synthetically generated labeled examples to enhance DCN training. Including diverse synthetic labeled seismic in training helps the network generalize enabling it to accurately predict seismic attribute values on field-acquired seismic surveys. Once trained, our DCN tool generates attributes with no input parameters and no additional user guidance. The DCN attribute computations are virtually indistinguishable from conventionally computed attributes while computing up to 100 times faster.

scholarly journals ResMem-Net: memory based deep CNN for image memorability estimation

2021 ◽  
Vol 7 ◽  
pp. e767
Author(s):  
Arockia Praveen ◽  
Abdulfattah Noorwali ◽  
Duraimurugan Samiayya ◽  
Mohammad Zubair Khan ◽  
Durai Raj Vincent P M ◽  
...  
Keyword(s):  
Deep Learning ◽  
Large Scale ◽  
Mean Squared Error ◽  
State Of The Art ◽  
Rank Correlation ◽  
Current State ◽  
Intermediate Layers ◽  
Better Than ◽  
Made In ◽  
Memory Efficient

Image memorability is a very hard problem in image processing due to its subjective nature. But due to the introduction of Deep Learning and the large availability of data and GPUs, great strides have been made in predicting the memorability of an image. In this paper, we propose a novel deep learning architecture called ResMem-Net that is a hybrid of LSTM and CNN that uses information from the hidden layers of the CNN to compute the memorability score of an image. The intermediate layers are important for predicting the output because they contain information about the intrinsic properties of the image. The proposed architecture automatically learns visual emotions and saliency, shown by the heatmaps generated using the GradRAM technique. We have also used the heatmaps and results to analyze and answer one of the most important questions in image memorability: “What makes an image memorable?”. The model is trained and evaluated using the publicly available Large-scale Image Memorability dataset (LaMem) from MIT. The results show that the model achieves a rank correlation of 0.679 and a mean squared error of 0.011, which is better than the current state-of-the-art models and is close to human consistency (p = 0.68). The proposed architecture also has a significantly low number of parameters compared to the state-of-the-art architecture, making it memory efficient and suitable for production.

scholarly journals GenNet framework: interpretable deep learning for predicting phenotypes from genetic data

2021 ◽  
Vol 4 (1) ◽  
Author(s):  
Arno van Hilten ◽  
Steven A. Kushner ◽  
Manfred Kayser ◽  
M. Arfan Ikram ◽  
Hieab H. H. Adams ◽  
...  
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Complex Traits ◽  
Population Genomics ◽  
Endocrine System ◽  
Network Architectures ◽  
Eye Color ◽  
Learning Framework ◽  
Interpretable Models ◽  
Memory Efficient

AbstractApplying deep learning in population genomics is challenging because of computational issues and lack of interpretable models. Here, we propose GenNet, a novel open-source deep learning framework for predicting phenotypes from genetic variants. In this framework, interpretable and memory-efficient neural network architectures are constructed by embedding biologically knowledge from public databases, resulting in neural networks that contain only biologically plausible connections. We applied the framework to seventeen phenotypes and found well-replicated genes such as HERC2 and OCA2 for hair and eye color, and novel genes such as ZNF773 and PCNT for schizophrenia. Additionally, the framework identified ubiquitin mediated proteolysis, endocrine system and viral infectious diseases as most predictive biological pathways for schizophrenia. GenNet is a freely available, end-to-end deep learning framework that allows researchers to develop and use interpretable neural networks to obtain novel insights into the genetic architecture of complex traits and diseases.

scholarly journals Memory-Efficient Deep Learning for Botnet Attack Detection in IoT Networks

Electronics ◽  
2021 ◽  
Vol 10 (9) ◽  
pp. 1104
Author(s):  
Segun I. Popoola ◽  
Bamidele Adebisi ◽  
Ruth Ande ◽  
Mohammad Hammoudeh ◽  
Aderemi A. Atayero
Keyword(s):  
Deep Learning ◽  
Data Storage ◽  
Network Traffic ◽  
Classification Performance ◽  
Attack Detection ◽  
Training Data ◽  
Memory Space ◽  
Network Bandwidth ◽  
Deep Recurrent Neural Network ◽  
Memory Efficient

Cyber attackers exploit a network of compromised computing devices, known as a botnet, to attack Internet-of-Things (IoT) networks. Recent research works have recommended the use of Deep Recurrent Neural Network (DRNN) for botnet attack detection in IoT networks. However, for high feature dimensionality in the training data, high network bandwidth and a large memory space will be needed to transmit and store the data, respectively in IoT back-end server or cloud platform for Deep Learning (DL). Furthermore, given highly imbalanced network traffic data, the DRNN model produces low classification performance in minority classes. In this paper, we exploit the joint advantages of Long Short-Term Memory Autoencoder (LAE), Synthetic Minority Oversampling Technique (SMOTE), and DRNN to develop a memory-efficient DL method, named LS-DRNN. The effectiveness of this method is evaluated with the Bot-IoT dataset. Results show that the LAE method reduced the dimensionality of network traffic features in the training set from 37 to 10, and this consequently reduced the memory space required for data storage by 86.49%. SMOTE method helped the LS-DRNN model to achieve high classification performance in minority classes, and the overall detection rate increased by 10.94%. Furthermore, the LS-DRNN model outperformed state-of-the-art models.

Deep Learning

2009 ◽  
Author(s):  
Stellan Ohlsson
Keyword(s):  
Deep Learning

Intelligence artificielle : le futur de l’Orthodontie ?

2019 ◽  
Vol 53 (3) ◽  
pp. 281-294
Author(s):  
Jean-Michel Foucart ◽  
Augustin Chavanne ◽  
Jérôme Bourriau
Keyword(s):  
Big Data ◽  
Deep Learning ◽  
Intelligence Artificielle ◽  
Set Up

Nombreux sont les apports envisagés de l’Intelligence Artificielle (IA) en médecine. En orthodontie, plusieurs solutions automatisées sont disponibles depuis quelques années en imagerie par rayons X (analyse céphalométrique automatisée, analyse automatisée des voies aériennes) ou depuis quelques mois (analyse automatique des modèles numériques, set-up automatisé; CS Model +, Carestream Dental™). L’objectif de cette étude, en deux parties, est d’évaluer la fiabilité de l’analyse automatisée des modèles tant au niveau de leur numérisation que de leur segmentation. La comparaison des résultats d’analyse des modèles obtenus automatiquement et par l’intermédiaire de plusieurs orthodontistes démontre la fiabilité de l’analyse automatique; l’erreur de mesure oscillant, in fine, entre 0,08 et 1,04 mm, ce qui est non significatif et comparable avec les erreurs de mesures inter-observateurs rapportées dans la littérature. Ces résultats ouvrent ainsi de nouvelles perspectives quand à l’apport de l’IA en Orthodontie qui, basée sur le deep learning et le big data, devrait permettre, à moyen terme, d’évoluer vers une orthodontie plus préventive et plus prédictive.

Sign in / Sign up

Export Citation Format

Share Document