Editorial introduction to the Neural Networks special issue on Deep Learning of Representations

2015 ◽  
Vol 64 ◽  
pp. 1-3 ◽  
Author(s):  
Yoshua Bengio ◽  
Honglak Lee
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Editorial Introduction ◽  
Special Issue ◽  
The Neural Networks

How Deep Learning Works: Inside the Neural Networks that Power Today's AI

IEEE Spectrum ◽  
2021 ◽  
Vol 58 (10) ◽  
pp. 32-33
Author(s):  
Samuel K. Moore ◽  
David Schneider ◽  
Eliza Strickland
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
The Neural Networks

Guest Editor’s Introduction: Software Mathematical Models for Human Understanding

2020 ◽  
Vol 30 (10) ◽  
pp. 1371-1374
Author(s):  
Iaakov Exman
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Systems Design ◽  
Difficult Problem ◽  
The Other ◽  
Software Systems ◽  
Special Issue ◽  
Software Developers ◽  
Human Understanding ◽  
Introductory Paper

The unrelenting trend of larger and larger sizes of Software Systems and data has made software comprehensibility an increasingly difficult problem. However, a tacit consensus that human understanding of software is essential for most software related activities, stimulated software developers to embed comprehensibility in their systems’ design. On the other hand, recent empirical successes of Deep Learning neural networks, in several application areas, seem to challenge the tacit consensus: is software comprehensibility a necessity, or just superfluous? This introductory paper, to the 2020 special issue on Theoretical Software Engineering, offers reasons justifying our standpoint on the referred controversy. This paper also points out to specific techniques enabling Human Understanding of software systems relevant to this issue’s papers.

scholarly journals Gender recognition in the wild: a robustness evaluation over corrupted images

2020 ◽  
Author(s):  
Antonio Greco ◽  
Alessia Saggese ◽  
Mario Vento ◽  
Vincenzo Vigilante
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Network Architectures ◽  
Gender Recognition ◽  
Face Images ◽  
The Face ◽  
In The Wild ◽  
The Neural Networks ◽  
The Common ◽  
And Gender

AbstractIn the era of deep learning, the methods for gender recognition from face images achieve remarkable performance over most of the standard datasets. However, the common experimental analyses do not take into account that the face images given as input to the neural networks are often affected by strong corruptions not always represented in standard datasets. In this paper, we propose an experimental framework for gender recognition “in the wild”. We produce a corrupted version of the popular LFW+ and GENDER-FERET datasets, that we call LFW+C and GENDER-FERET-C, and evaluate the accuracy of nine different network architectures in presence of specific, suitably designed, corruptions; in addition, we perform an experiment on the MIVIA-Gender dataset, recorded in real environments, to analyze the effects of mixed image corruptions happening in the wild. The experimental analysis demonstrates that the robustness of the considered methods can be further improved, since all of them are affected by a performance drop on images collected in the wild or manually corrupted. Starting from the experimental results, we are able to provide useful insights for choosing the best currently available architecture in specific real conditions. The proposed experimental framework, whose code is publicly available, is general enough to be applicable also on different datasets; thus, it can act as a forerunner for future investigations.

scholarly journals CNN-based Single-Fault Diagnosis of Self-Priming Centrifugal Pump

2019 ◽  
Vol 9 (1) ◽  
pp. 1839-1848
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Fault Diagnosis ◽  
Classification Accuracy ◽  
Centrifugal Pumps ◽  
Good Classification ◽  
Learning Technique ◽  
The Neural Networks ◽  
Classification Time

CNN is a very powerful deep learning technique for classification when the size of data is significant. It has been observed that it fails to give any reasonable classification when size of the data is small. This paper deals with an enhanced data technique, which is very useful for smaller size of available data. We proposed to increase the size of data to multiple times until a good classification accuracy is acquired. The paper shows that the neural networks perform very efficiently when such type of enhancement is done. It has been elaborated for evaluating the classification of faults of centrifugal pumps. The CNN-2D and CNN-1D yield 100% accuracy for diagnosing the faults of in this case. The performance is also compared with that of ANN. The number of epochs required to reach 100% accuracy for multiple different sizes of data is used to evaluate the performance. The enhanced data approach also shows that there is a drastic fall in overall classification time of CNN.

scholarly journals Systems biology informed deep learning for inferring parameters and hidden dynamics

2019 ◽  
Author(s):  
Alireza Yazdani ◽  
Lu Lu ◽  
Maziar Raissi ◽  
George Em Karniadakis
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Systems Biology ◽  
Differential Equations ◽  
Ordinary Differential Equations ◽  
System Level ◽  
Model Parameters ◽  
Unknown Parameters ◽  
The Neural Networks ◽  
Noisy Measurements

AbstractMathematical models of biological reactions at the system-level lead to a set of ordinary differential equations with many unknown parameters that need to be inferred using relatively few experimental measurements. Having a reliable and robust algorithm for parameter inference and prediction of the hidden dynamics has been one of the core subjects in systems biology, and is the focus of this study. We have developed a new systems-biology-informed deep learning algorithm that incorporates the system of ordinary differential equations into the neural networks. Enforcing these equations effectively adds constraints to the optimization procedure that manifests itself as an imposed structure on the observational data. Using few scattered and noisy measurements, we are able to infer the dynamics of unobserved species, external forcing, and the unknown model parameters. We have successfully tested the algorithm for three different benchmark problems.Author summaryThe dynamics of systems biological processes are usually modeled using ordinary differential equations (ODEs), which introduce various unknown parameters that need to be estimated efficiently from noisy measurements of concentration for a few species only. In this work, we present a new “systems-informed neural network” to infer the dynamics of experimentally unobserved species as well as the unknown parameters in the system of equations. By incorporating the system of ODEs into the neural networks, we effectively add constraints to the optimization algorithm, which makes the method robust to noisy and sparse measurements.

Toward Multi-FPGA Acceleration of the Neural Networks

2021 ◽  
Vol 17 (2) ◽  
pp. 1-23
Author(s):  
Saman Biookaghazadeh ◽  
Pravin Kumar Ravi ◽  
Ming Zhao
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
High Performance ◽  
Low Latency ◽  
Fpga Design ◽  
Area Efficiency ◽  
Linear Speedup ◽  
The Neural Networks ◽  
Fpga Acceleration

High-throughput and low-latency Convolutional Neural Network (CNN) inference is increasingly important for many cloud- and edge-computing applications. FPGA-based acceleration of CNN inference has demonstrated various benefits compared to other high-performance devices such as GPGPUs. Current FPGA CNN-acceleration solutions are based on a single FPGA design, which are limited by the available resources on an FPGA. In addition, they can only accelerate conventional 2D neural networks. To address these limitations, we present a generic multi-FPGA solution, written in OpenCL, which can accelerate more complex CNNs (e.g., C3D CNN) and achieve a near linear speedup with respect to the available single-FPGA solutions. The design is built upon the Intel Deep Learning Accelerator architecture, with three extensions. First, it includes updates for better area efficiency (up to 25%) and higher performance (up to 24%). Second, it supports 3D convolutions for more challenging applications such as video learning. Third, it supports multi-FPGA communication for higher inference throughput. The results show that utilizing multiple FPGAs can linearly increase the overall bandwidth while maintaining the same end-to-end latency. In addition, the design can outperform other FPGA 2D accelerators by up to 8.4 times and 3D accelerators by up to 1.7 times.

scholarly journals COMPUTER VISION FOR HUMAN-MACHINE INTERACTION-REVIEW

2019 ◽  
Vol 2019 (02) ◽  
pp. 131-139 ◽  
Author(s):  
Dr. Suma V.
Keyword(s):  
Artificial Intelligence ◽  
Neural Networks ◽  
Computer Vision ◽  
Deep Learning ◽  
Human Vision ◽  
Human Machine Interaction ◽  
The Neural Networks ◽  
Security Surveillance ◽  
Heath Care ◽  
Machine Interaction

The paper is a review on the computer vision that is helpful in the interaction between the human and the machines. The computer vision that is termed as the subfield of the artificial intelligence and the machine learning is capable of training the computer to visualize, interpret and respond back to the visual world in a similar way as the human vision does. Nowadays the computer vision has found its application in broader areas such as the heath care, safety security, surveillance etc. due to the progress, developments and latest innovations in the artificial intelligence, deep learning and neural networks. The paper presents the enhanced capabilities of the computer vision experienced in various applications related to the interactions between the human and machines involving the artificial intelligence, deep learning and the neural networks.

Sign in / Sign up

Export Citation Format

Share Document