scholarly journals BPLight-CNN: A Photonics-Based Backpropagation Accelerator for Deep Learning

2021 ◽  
Vol 17 (4) ◽  
pp. 1-26
Author(s):  
Dharanidhar Dang ◽  
Sai Vineel Reddy Chittamuru ◽  
Sudeep Pasricha ◽  
Rabi Mahapatra ◽  
Debashis Sahoo
Keyword(s):  
Deep Learning ◽  
Computational Efficiency ◽  
High Performance ◽  
Energy Savings ◽  
State Of The Art ◽  
The State ◽  
Bp Algorithm ◽  
Learning Networks ◽  
Training Module ◽  
Lower Accuracy

Training deep learning networks involves continuous weight updates across the various layers of the deep network while using a backpropagation (BP) algorithm. This results in expensive computation overheads during training. Consequently, most deep learning accelerators today employ pretrained weights and focus only on improving the design of the inference phase. The recent trend is to build a complete deep learning accelerator by incorporating the training module. Such efforts require an ultra-fast chip architecture for executing the BP algorithm. In this article, we propose a novel photonics-based backpropagation accelerator for high-performance deep learning training. We present the design for a convolutional neural network (CNN), BPLight-CNN , which incorporates the silicon photonics-based backpropagation accelerator. BPLight-CNN is a first-of-its-kind photonic and memristor-based CNN architecture for end-to-end training and prediction. We evaluate BPLight-CNN using a photonic CAD framework (IPKISS) on deep learning benchmark models, including LeNet and VGG-Net. The proposed design achieves (i) at least 34× speedup, 34× improvement in computational efficiency, and 38.5× energy savings during training; and (ii) 29× speedup, 31× improvement in computational efficiency, and 38.7× improvement in energy savings during inference compared with the state-of-the-art designs. All of these comparisons are done at a 16-bit resolution, and BPLight-CNN achieves these improvements at a cost of approximately 6% lower accuracy compared with the state-of-the-art.

scholarly journals Representation Learning for Fine-Grained Change Detection

Sensors ◽  
2021 ◽  
Vol 21 (13) ◽  
pp. 4486
Author(s):  
Niall O’Mahony ◽  
Sean Campbell ◽  
Lenka Krpalkova ◽  
Anderson Carvalho ◽  
Joseph Walsh ◽  
...  
Keyword(s):  
Deep Learning ◽  
Change Detection ◽  
Model Calibration ◽  
State Of The Art ◽  
Representation Learning ◽  
Machine Intelligence ◽  
The State ◽  
Sensor Data ◽  
Fine Grained ◽  
Learning Techniques

Fine-grained change detection in sensor data is very challenging for artificial intelligence though it is critically important in practice. It is the process of identifying differences in the state of an object or phenomenon where the differences are class-specific and are difficult to generalise. As a result, many recent technologies that leverage big data and deep learning struggle with this task. This review focuses on the state-of-the-art methods, applications, and challenges of representation learning for fine-grained change detection. Our research focuses on methods of harnessing the latent metric space of representation learning techniques as an interim output for hybrid human-machine intelligence. We review methods for transforming and projecting embedding space such that significant changes can be communicated more effectively and a more comprehensive interpretation of underlying relationships in sensor data is facilitated. We conduct this research in our work towards developing a method for aligning the axes of latent embedding space with meaningful real-world metrics so that the reasoning behind the detection of change in relation to past observations may be revealed and adjusted. This is an important topic in many fields concerned with producing more meaningful and explainable outputs from deep learning and also for providing means for knowledge injection and model calibration in order to maintain user confidence.

Named Entity Recognition and Relation Extraction

2021 ◽  
Vol 54 (1) ◽  
pp. 1-39
Author(s):  
Zara Nasar ◽  
Syed Waqar Jaffry ◽  
Muhammad Kamran Malik
Keyword(s):  
Deep Learning ◽  
State Of The Art ◽  
Named Entity Recognition ◽  
Relation Extraction ◽  
The State ◽  
Entity Recognition ◽  
Joint Models ◽  
Named Entity ◽  
Textual Data ◽  
Benchmark Datasets

With the advent of Web 2.0, there exist many online platforms that result in massive textual-data production. With ever-increasing textual data at hand, it is of immense importance to extract information nuggets from this data. One approach towards effective harnessing of this unstructured textual data could be its transformation into structured text. Hence, this study aims to present an overview of approaches that can be applied to extract key insights from textual data in a structured way. For this, Named Entity Recognition and Relation Extraction are being majorly addressed in this review study. The former deals with identification of named entities, and the latter deals with problem of extracting relation between set of entities. This study covers early approaches as well as the developments made up till now using machine learning models. Survey findings conclude that deep-learning-based hybrid and joint models are currently governing the state-of-the-art. It is also observed that annotated benchmark datasets for various textual-data generators such as Twitter and other social forums are not available. This scarcity of dataset has resulted into relatively less progress in these domains. Additionally, the majority of the state-of-the-art techniques are offline and computationally expensive. Last, with increasing focus on deep-learning frameworks, there is need to understand and explain the under-going processes in deep architectures.

Advancing the state of the art in high-performance logic and array technology

1992 ◽  
Vol 36 (5) ◽  
pp. 821-828 ◽  
Author(s):  
K. H. Brown ◽  
D. A. Grose ◽  
R. C. Lange ◽  
T. H. Ning ◽  
P. A. Totta
Keyword(s):  
High Performance ◽  
State Of The Art ◽  
The State ◽  
Array Technology

BISWSRBS: A Winograd-based CNN Accelerator with a Fine-grained Regular Sparsity Pattern and Mixed Precision Quantization

2021 ◽  
Vol 14 (4) ◽  
pp. 1-28
Author(s):  
Tao Yang ◽  
Zhezhi He ◽  
Tengchuan Kou ◽  
Qingzheng Li ◽  
Qi Han ◽  
...  
Keyword(s):  
High Performance ◽  
State Of The Art ◽  
The State ◽  
Optimization Approach ◽  
Quantization Scheme ◽  
Model Accuracy ◽  
Sparsity Pattern ◽  
Computing Platform ◽  
Energy Efficiency Improvement ◽  
Mixed Precision

Field-programmable Gate Array (FPGA) is a high-performance computing platform for Convolution Neural Networks (CNNs) inference. Winograd algorithm, weight pruning, and quantization are widely adopted to reduce the storage and arithmetic overhead of CNNs on FPGAs. Recent studies strive to prune the weights in the Winograd domain, however, resulting in irregular sparse patterns and leading to low parallelism and reduced utilization of resources. Besides, there are few works to discuss a suitable quantization scheme for Winograd. In this article, we propose a regular sparse pruning pattern in the Winograd-based CNN, namely, Sub-row-balanced Sparsity (SRBS) pattern, to overcome the challenge of the irregular sparse pattern. Then, we develop a two-step hardware co-optimization approach to improve the model accuracy using the SRBS pattern. Based on the pruned model, we implement a mixed precision quantization to further reduce the computational complexity of bit operations. Finally, we design an FPGA accelerator that takes both the advantage of the SRBS pattern to eliminate low-parallelism computation and the irregular memory accesses, as well as the mixed precision quantization to get a layer-wise bit width. Experimental results on VGG16/VGG-nagadomi with CIFAR-10 and ResNet-18/34/50 with ImageNet show up to 11.8×/8.67× and 8.17×/8.31×/10.6× speedup, 12.74×/9.19× and 8.75×/8.81×/11.1× energy efficiency improvement, respectively, compared with the state-of-the-art dense Winograd accelerator [20] with negligible loss of model accuracy. We also show that our design has 4.11× speedup compared with the state-of-the-art sparse Winograd accelerator [19] on VGG16.

Ensemble-based deep meta learning for medical image segmentation

2021 ◽  
pp. 1-7
Author(s):  
Usman Ahmed ◽  
Jerry Chun-Wei Lin ◽  
Gautam Srivastava
Keyword(s):  
Image Segmentation ◽  
Deep Learning ◽  
Learning Algorithm ◽  
State Of The Art ◽  
Medical Image Segmentation ◽  
The State ◽  
Data Set ◽  
Deep Learning Algorithm ◽  
Meta Learning ◽  
Small Set

Deep learning methods have led to a state of the art medical applications, such as image classification and segmentation. The data-driven deep learning application can help stakeholders to collaborate. However, limited labelled data set limits the deep learning algorithm to generalize for one domain into another. To handle the problem, meta-learning helps to learn from a small set of data. We proposed a meta learning-based image segmentation model that combines the learning of the state-of-the-art model and then used it to achieve domain adoption and high accuracy. Also, we proposed a prepossessing algorithm to increase the usability of the segments part and remove noise from the new test image. The proposed model can achieve 0.94 precision and 0.92 recall. The ability to increase 3.3% among the state-of-the-art algorithms.

Fauce

2021 ◽  
Vol 14 (11) ◽  
pp. 1950-1963
Author(s):  
Jie Liu ◽  
Wenqian Dong ◽  
Qingqing Zhou ◽  
Dong Li
Keyword(s):  
Deep Learning ◽  
State Of The Art ◽  
The State ◽  
Light Weight ◽  
Critical Problem ◽  
Estimation Errors ◽  
Cardinality Estimation ◽  
Complex Queries ◽  
Uncertainty Information ◽  
Deep Learning Model

Cardinality estimation is a fundamental and critical problem in databases. Recently, many estimators based on deep learning have been proposed to solve this problem and they have achieved promising results. However, these estimators struggle to provide accurate results for complex queries, due to not capturing real inter-column and inter-table correlations. Furthermore, none of these estimators contain the uncertainty information about their estimations. In this paper, we present a join cardinality estimator called Fauce. Fauce learns the correlations across all columns and all tables in the database. It also contains the uncertainty information of each estimation. Among all studied learned estimators, our results are promising: (1) Fauce is a light-weight estimator, it has 10× faster inference speed than the state of the art estimator; (2) Fauce is robust to the complex queries, it provides 1.3×--6.7× smaller estimation errors for complex queries compared with the state of the art estimator; (3) To the best of our knowledge, Fauce is the first estimator that incorporates uncertainty information for cardinality estimation into a deep learning model.

Deep Learning Model for Imbalanced Multi-label Surface Defect Classification

2021 ◽  
Author(s):  
Yang Liu ◽  
Yachao Yuan ◽  
Jing Liu
Keyword(s):  
Deep Learning ◽  
Surface Defect ◽  
State Of The Art ◽  
Steel Production ◽  
Learning Model ◽  
The State ◽  
Low Latency ◽  
Defect Classification ◽  
Key Techniques ◽  
Deep Learning Model

Abstract Automatic defect classification is vital to ensure product quality, especially for steel production. In the real world, the amount of collected samples with labels is limited due to high labor costs, and the gathered dataset is usually imbalanced, making accurate steel defect classification very challenging. In this paper, a novel deep learning model for imbalanced multi-label surface defect classification, named ImDeep, is proposed. It can be deployed easily in steel production lines to identify different defect types on the steel's surface. ImDeep incorporates three key techniques, i.e., Imbalanced Sampler, Fussy-FusionNet, and Transfer Learning. It improves the model's classification performance with multi-label and reduces the model's complexity over small datasets with low latency. The performance of different fusion strategies and three key techniques of ImDeep is verified. Simulation results prove that ImDeep accomplishes better performance than the state-of-the-art over the public dataset with varied sizes. Specifically, ImDeep achieves about 97% accuracy of steel surface defect classification over a small imbalanced dataset with a low latency, which improves about 10% compared with that of the state-of-the-art.

scholarly journals Visual-Based Defect Detection and Classification Approaches for Industrial Applications—A SURVEY

Sensors ◽  
2020 ◽  
Vol 20 (5) ◽  
pp. 1459 ◽  
Author(s):  
Tamás Czimmermann ◽  
Gastone Ciuti ◽  
Mario Milazzo ◽  
Marcello Chiurazzi ◽  
Stefano Roccella ◽  
...  
Keyword(s):  
Deep Learning ◽  
Defect Detection ◽  
Visual Processing ◽  
State Of The Art ◽  
Industrial Applications ◽  
The State ◽  
Shape Error ◽  
Supervised Classifiers ◽  
Processing Techniques

This paper reviews automated visual-based defect detection approaches applicable to various materials, such as metals, ceramics and textiles. In the first part of the paper, we present a general taxonomy of the different defects that fall in two classes: visible (e.g., scratches, shape error, etc.) and palpable (e.g., crack, bump, etc.) defects. Then, we describe artificial visual processing techniques that are aimed at understanding of the captured scenery in a mathematical/logical way. We continue with a survey of textural defect detection based on statistical, structural and other approaches. Finally, we report the state of the art for approaching the detection and classification of defects through supervised and non-supervised classifiers and deep learning.

scholarly journals Complex Data Imputation by Auto-Encoders and Convolutional Neural Networks—A Case Study on Genome Gap-Filling

Computers ◽  
2020 ◽  
Vol 9 (2) ◽  
pp. 37 ◽  
Author(s):  
Luca Cappelletti ◽  
Tommaso Fontana ◽  
Guido Walter Di Donato ◽  
Lorenzo Di Tucci ◽  
Elena Casiraghi ◽  
...  
Keyword(s):  
Deep Learning ◽  
Missing Data ◽  
State Of The Art ◽  
The State ◽  
Complex Data ◽  
Data Imputation ◽  
Genome Sequences ◽  
Missing Data Imputation ◽  
The Past ◽  
Learning Techniques

Missing data imputation has been a hot topic in the past decade, and many state-of-the-art works have been presented to propose novel, interesting solutions that have been applied in a variety of fields. In the past decade, the successful results achieved by deep learning techniques have opened the way to their application for solving difficult problems where human skill is not able to provide a reliable solution. Not surprisingly, some deep learners, mainly exploiting encoder-decoder architectures, have also been designed and applied to the task of missing data imputation. However, most of the proposed imputation techniques have not been designed to tackle “complex data”, that is high dimensional data belonging to datasets with huge cardinality and describing complex problems. Precisely, they often need critical parameters to be manually set or exploit complex architecture and/or training phases that make their computational load impracticable. In this paper, after clustering the state-of-the-art imputation techniques into three broad categories, we briefly review the most representative methods and then describe our data imputation proposals, which exploit deep learning techniques specifically designed to handle complex data. Comparative tests on genome sequences show that our deep learning imputers outperform the state-of-the-art KNN-imputation method when filling gaps in human genome sequences.

Sign in / Sign up

Export Citation Format

Share Document