Accelerating Large-Scale Deep Convolutional Neural Networks on Multi-core Vector Accelerators

2021 ◽  
pp. 68-79
Author(s):  
Zhong Liu ◽  
Sheng Ma ◽  
Cheng Li ◽  
Haiyan Chen
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Large Scale ◽  
Deep Convolutional Neural Networks

scholarly journals MS2CNN: predicting MS/MS spectrum based on protein sequence using deep convolutional neural networks

BMC Genomics ◽  
2019 ◽  
Vol 20 (S9) ◽  
Author(s):  
Yang-Ming Lin ◽  
Ching-Tai Chen ◽  
Jia-Ming Chang
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Networks ◽  
Large Scale ◽  
Learning Algorithm ◽  
Pearson Correlation ◽  
Tandem Mass ◽  
Spectral Library ◽  
Deep Convolutional Neural Networks ◽  
Library Search

Abstract Background Tandem mass spectrometry allows biologists to identify and quantify protein samples in the form of digested peptide sequences. When performing peptide identification, spectral library search is more sensitive than traditional database search but is limited to peptides that have been previously identified. An accurate tandem mass spectrum prediction tool is thus crucial in expanding the peptide space and increasing the coverage of spectral library search. Results We propose MS2CNN, a non-linear regression model based on deep convolutional neural networks, a deep learning algorithm. The features for our model are amino acid composition, predicted secondary structure, and physical-chemical features such as isoelectric point, aromaticity, helicity, hydrophobicity, and basicity. MS2CNN was trained with five-fold cross validation on a three-way data split on the large-scale human HCD MS2 dataset of Orbitrap LC-MS/MS downloaded from the National Institute of Standards and Technology. It was then evaluated on a publicly available independent test dataset of human HeLa cell lysate from LC-MS experiments. On average, our model shows better cosine similarity and Pearson correlation coefficient (0.690 and 0.632) than MS2PIP (0.647 and 0.601) and is comparable with pDeep (0.692 and 0.642). Notably, for the more complex MS2 spectra of 3+ peptides, MS2PIP is significantly better than both MS2PIP and pDeep. Conclusions We showed that MS2CNN outperforms MS2PIP for 2+ and 3+ peptides and pDeep for 3+ peptides. This implies that MS2CNN, the proposed convolutional neural network model, generates highly accurate MS2 spectra for LC-MS/MS experiments using Orbitrap machines, which can be of great help in protein and peptide identifications. The results suggest that incorporating more data for deep learning model may improve performance.

scholarly journals Spatio–Temporal Image Representation of 3D Skeletal Movements for View-Invariant Action Recognition with Deep Convolutional Neural Networks

Sensors ◽  
2019 ◽  
Vol 19 (8) ◽  
pp. 1932 ◽  
Author(s):  
Huy Hieu Pham ◽  
Houssam Salmane ◽  
Louahdi Khoudour ◽  
Alain Crouzil ◽  
Pablo Zegers ◽  
...  
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Action Recognition ◽  
Large Scale ◽  
Image Representation ◽  
Human Action ◽  
Computational Time ◽  
Deep Convolutional Neural Networks ◽  
Classification Tasks ◽  
Spatio Temporal

Designing motion representations for 3D human action recognition from skeleton sequences is an important yet challenging task. An effective representation should be robust to noise, invariant to viewpoint changes and result in a good performance with low-computational demand. Two main challenges in this task include how to efficiently represent spatio–temporal patterns of skeletal movements and how to learn their discriminative features for classification tasks. This paper presents a novel skeleton-based representation and a deep learning framework for 3D action recognition using RGB-D sensors. We propose to build an action map called SPMF (Skeleton Posture-Motion Feature), which is a compact image representation built from skeleton poses and their motions. An Adaptive Histogram Equalization (AHE) algorithm is then applied on the SPMF to enhance their local patterns and form an enhanced action map, namely Enhanced-SPMF. For learning and classification tasks, we exploit Deep Convolutional Neural Networks based on the DenseNet architecture to learn directly an end-to-end mapping between input skeleton sequences and their action labels via the Enhanced-SPMFs. The proposed method is evaluated on four challenging benchmark datasets, including both individual actions, interactions, multiview and large-scale datasets. The experimental results demonstrate that the proposed method outperforms previous state-of-the-art approaches on all benchmark tasks, whilst requiring low computational time for training and inference.

scholarly journals Leveraging the Generalization Ability of Deep Convolutional Neural Networks for Improving Classifiers for Color Fundus Photographs

2021 ◽  
Vol 11 (2) ◽  
pp. 591
Author(s):  
Jaemin Son ◽  
Jaeyoung Kim ◽  
Seo Taek Kong ◽  
Kyu-Hwan Jung
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Large Scale ◽  
Validation Dataset ◽  
Deep Convolutional Neural Networks ◽  
Pathological Myopia ◽  
Annotation Task ◽  
Generalization Ability ◽  
Source Codes ◽  
Fundus Photographs

Deep learning demands a large amount of annotated data, and the annotation task is often crowdsourced for economic efficiency. When the annotation task is delegated to non-experts, the dataset may contain data with inaccurate labels. Noisy labels not only yield classification models with sub-optimal performance, but may also impede their optimization dynamics. In this work, we propose exploiting the pattern recognition capacity of deep convolutional neural networks to filter out supposedly mislabeled cases while training. We suggest a training method that references softmax outputs to judge the correctness of the given labels. This approach achieved outstanding performance compared to the existing methods in various noise settings on a large-scale dataset (Kaggle 2015 Diabetic Retinopathy). Furthermore, we demonstrate a method mining positive cases from a pool of unlabeled images by exploiting the generalization ability. With this method, we won first place on the offsite validation dataset in pathological myopia classification challenge (PALM), achieving the AUROC of 0.9993 in the final submission. Source codes are publicly available.

A novel MapReduce-based deep convolutional neural network algorithm

2021 ◽  
pp. 1-13
Author(s):  
Xiang-Min Liu ◽  
Jian Hu ◽  
Deborah Simon Mwakapesa ◽  
Y.A. Nanehkaran ◽  
Yi-Min Mao ◽  
...  
Keyword(s):  
Neural Networks ◽  
Big Data ◽  
Convolutional Neural Networks ◽  
Large Scale ◽  
Feature Learning ◽  
Deep Convolutional Neural Networks ◽  
Network Training ◽  
Load Rate ◽  
Data Environment ◽  
Neural Networks Optimization

Deep convolutional neural networks (DCNNs), with their complex network structure and powerful feature learning and feature expression capabilities, have been remarkable successes in many large-scale recognition tasks. However, with the expectation of memory overhead and response time, along with the increasing scale of data, DCNN faces three non-rival challenges in a big data environment: excessive network parameters, slow convergence, and inefficient parallelism. To tackle these three problems, this paper develops a deep convolutional neural networks optimization algorithm (PDCNNO) in the MapReduce framework. The proposed method first pruned the network to obtain a compressed network in order to effectively reduce redundant parameters. Next, a conjugate gradient method based on modified secant equation (CGMSE) is developed in the Map phase to further accelerate the convergence of the network. Finally, a load balancing strategy based on regulate load rate (LBRLA) is proposed in the Reduce phase to quickly achieve equal grouping of data and thus improving the parallel performance of the system. We compared the PDCNNO algorithm with other algorithms on three datasets, including SVHN, EMNIST Digits, and ISLVRC2012. The experimental results show that our algorithm not only reduces the space and time overhead of network training but also obtains a well-performing speed-up ratio in a big data environment.

scholarly journals Baryon acoustic oscillations reconstruction using convolutional neural networks

2020 ◽  
Vol 501 (1) ◽  
pp. 1499-1510
Author(s):  
Tian-Xiang Mao ◽  
Jie Wang ◽  
Baojiu Li ◽  
Yan-Chuan Cai ◽  
Bridget Falck ◽  
...  
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Large Scale ◽  
Initial Conditions ◽  
Signal To Noise Ratio ◽  
Fine Tuning ◽  
Reconstruction Method ◽  
Acoustic Oscillations ◽  
Deep Convolutional Neural Networks ◽  
Baryon Acoustic Oscillations

ABSTRACT We propose a new scheme to reconstruct the baryon acoustic oscillations (BAO) signal, which contains key cosmological information, based on deep convolutional neural networks (CNN). Trained with almost no fine tuning, the network can recover large-scale modes accurately in the test set: the correlation coefficient between the true and reconstructed initial conditions reaches $90{{\ \rm per\ cent}}$ at $k\le 0.2 \, h\mathrm{Mpc}^{-1}$, which can lead to significant improvements of the BAO signal-to-noise ratio down to $k\simeq 0.4\, h\mathrm{Mpc}^{-1}$. Since this new scheme is based on the configuration-space density field in sub-boxes, it is local and less affected by survey boundaries than the standard reconstruction method, as our tests confirm. We find that the network trained in one cosmology is able to reconstruct BAO peaks in the others, i.e. recovering information lost to non-linearity independent of cosmology. The accuracy of recovered BAO peak positions is far less than that caused by the difference in the cosmology models for training and testing, suggesting that different models can be distinguished efficiently in our scheme. It is very promising that our scheme provides a different new way to extract the cosmological information from the ongoing and future large galaxy surveys.

scholarly journals Spatio-Temporal Image Representation of 3D Skeletal Movements for View-Invariant Action Recognition with Deep Convolutional Neural Networks

2019 ◽  
Author(s):  
Huy Hieu Pham ◽  
Houssam Salmane ◽  
Louahdi Khoudour ◽  
Alain Crouzil ◽  
Pablo Zegers ◽  
...  
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Action Recognition ◽  
Large Scale ◽  
Image Representation ◽  
Human Action ◽  
Computational Time ◽  
Deep Convolutional Neural Networks ◽  
Motion Feature ◽  
Spatio Temporal

Designing motion representations for the problem of 3D human action recognition from skeleton sequences is an important yet challenging task. An effective representation should be robust to noise, invariant to viewpoint changes and result in a good performance with low-computational demand. Two main challenges in this task include how to efficiently represent spatio-temporal patterns of skeletal movements and how to learn their discriminative features for classification task. This paper presents a novel skeleton-based representation and a deep learning framework for 3D action recognition using RGB-D sensors. We propose to build an action map called SPMF (Skeleton Posture-Motion Feature), which is a compact image representation built from skeleton poses and their motions. An Adaptive Histogram Equalization (AHE) algorithm is then applied on the SPMF to enhance their local patterns and form an enhanced action map, namely Enhanced-SPMF. For learning and classification tasks, we exploit Deep Convolutional Neural Networks based on the DenseNet architecture to learn directly an end-to-end mapping between input skeleton sequences and their action labels via the Enhanced-SPMFs. The proposed method is evaluated on four challenging benchmark datasets, including both individual actions, interactions, multiview and large-scale datasets. The experimental results demonstrate that the proposed method outperforms previous state-of-the-art approaches on all benchmark tasks, whilst requiring low computational time for training and inference.

scholarly journals Deep convolutional neural networks as strong gravitational lens detectors

2018 ◽  
Vol 611 ◽  
pp. A2 ◽  
Author(s):  
C. Schaefer ◽  
M. Geiger ◽  
T. Kuntzer ◽  
J.-P. Kneib
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Large Scale ◽  
Characteristic Curve ◽  
Simulated Data ◽  
Large Data ◽  
Gravitational Lens ◽  
Deep Convolutional Neural Networks ◽  
Data Set ◽  
Strong Lensing

Context. Future large-scale surveys with high-resolution imaging will provide us with approximately 105 new strong galaxy-scale lenses. These strong-lensing systems will be contained in large data amounts, however, which are beyond the capacity of human experts to visually classify in an unbiased way. Aims. We present a new strong gravitational lens finder based on convolutional neural networks (CNNs). The method was applied to the strong-lensing challenge organized by the Bologna Lens Factory. It achieved first and third place, respectively, on the space-based data set and the ground-based data set. The goal was to find a fully automated lens finder for ground-based and space-based surveys that minimizes human inspection. Methods. We compared the results of our CNN architecture and three new variations (“invariant” “views” and “residual”) on the simulated data of the challenge. Each method was trained separately five times on 17 000 simulated images, cross-validated using 3000 images, and then applied to a test set with 100 000 images. We used two different metrics for evaluation, the area under the receiver operating characteristic curve (AUC) score, and the recall with no false positive (Recall0FP). Results. For ground-based data, our best method achieved an AUC score of 0.977 and a Recall0FP of 0.50. For space-based data, our best method achieved an AUC score of 0.940 and a Recall0FP of 0.32. Adding dihedral invariance to the CNN architecture diminished the overall score on space-based data, but achieved a higher no-contamination recall. We found that using committees of five CNNs produced the best recall at zero contamination and consistently scored better AUC than a single CNN. Conclusions. We found that for every variation of our CNN lensfinder, we achieved AUC scores close to 1 within 6%. A deeper network did not outperform simpler CNN models either. This indicates that more complex networks are not needed to model the simulated lenses. To verify this, more realistic lens simulations with more lens-like structures (spiral galaxies or ring galaxies) are needed to compare the performance of deeper and shallower networks.

Sign in / Sign up

Export Citation Format

Share Document