An Overview of Popular Deep Learning Methods

Coşkun, Musab; Yıldırım, Özal; Uçar, Ayşegül; Demir, Yakup

doi:10.23884/ejt.2017.7.2.11

Cited by 80 publications

(49 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Machine learning (ML) is a subset of artificial intelligence that occurred in 1980s and supports the modern society in many ways [41]. ML is a method that detect patterns automatically in data and then integrate this information to predict the future data [7].…”

Section: Machine Learningmentioning

confidence: 99%

“…The very significant property of DL techniques is that it can learn feature representations automatically therefore avoiding time-consuming. The considerable advances in the ML algorithms, and reasonable cost of computing hardware are mainly critical reasons for the deep learning booming [41]. DL uses learning methods of representation at multiple levels of abstraction to process input data without the need to engineer manual feature for automatic recognition of intricate structures in high-dimensional data.…”

Section: Deep Learningmentioning

confidence: 99%

See 1 more Smart Citation

Recent Innovations in Automated Detection and Classification of Diabetic Retinopathy

Aladawi¹,

Jayakumari²,

Sumesh³

et al. 2019

IJITEE

View full text Add to dashboard Cite

Due to the increasing prevalence of diabetic retinopathy worldwide, it’s an urgent need to develop smart system that help to detect disease using one of the modern technologies. Artificial intelligence is one of the popular techniques nowadays which has the ability to learn from experience and carry out human-like tasks. Large number of researches have been conducted to find out effective medical diagnosis methods for numerous diseases. Likewise, huge number of researches have been done that discuss automated detection and classification of diabetic retinopathy. This paper reviews the existing methodologies, datasets, sensitivity, specificity and classification accuracy in diabetic retinopathy.

show abstract

Section: Machine Learningmentioning

confidence: 99%

Section: Deep Learningmentioning

confidence: 99%

Recent Innovations in Automated Detection and Classification of Diabetic Retinopathy

Aladawi¹,

Jayakumari²,

Sumesh³

et al. 2019

IJITEE

View full text Add to dashboard Cite

show abstract

“…In the modern DNN algorithms, matrix multiplication is an essential building block and constitutes 70-80% of the work-load for the DNN training process because it is carried out for more number of times during the training of DNN. As the matrix multiplication supports data parallelism, it can be done very efficiently by implementing it parallel using CUDA and executing on GPU [10]. In our previous work, we have used fast Winograd's matrix multiplication, fast parallel Winogard's matrix multiplication, and parallel blocked matrix multiplication with collapse clause for efficient training of DNN algorithms.…”

Section: Introductionmentioning

confidence: 99%

Accelerating Training of Deep Neural Networks on GPU using CUDA

Rao¹,

Ramana²

2019

IJISA

View full text Add to dashboard Cite

The development of fast and efficient training algorithms for Deep Neural Networks has been a subject of interest over the past few years because the biggest drawback of Deep Neural Networks is enormous cost in computation and large time is consumed to train the parameters of Deep Neural Networks. This aspect motivated several researchers to focus on recent advancements of hardware architectures and parallel programming models and paradigms for accelerating the training of Deep Neural Networks. We revisited the concepts and mechanisms of typical Deep Neural Network training algorithms such as Backpropagation Algorithm and Boltzmann Machine Algorithm and observed that the matrix multiplication constitutes major portion of the work-load for the Deep Neural Network training process because it is carried out for a huge number of times during the training of Deep Neural Networks. With the advent of many-core GPU technologies, a matrix multiplication can be done very efficiently in parallel and this helps a lot training a Deep Neural Network not consuming time as it used to be a few years ago. CUDA is one of the high performance parallel programming models to exploit the capabilities of modern many-core GPU systems. In this paper, we propose to modify Backpropagation Algorithm and Boltzmann Machine Algorithm with CUDA parallel matrix multiplication and test on many-core GPU system. Finally we discover that the planned strategies achieve very quick training of Deep Neural Networks than classic strategies.

show abstract

“…At present, many methods have been developed in the classification of images. Deep learning is at the forefront of the modern methods used for this purpose [10], [11]. Deep learning occurs with the use of advanced technology, such as multilayer neural networks, to create systems that can identify properties with feature extraction methods from unlabeled training data, especially in large quantities.…”

Section: Introductionmentioning

confidence: 99%

Recognition of Road Type and Quality for Advanced Driver Assistance Systems with Deep Learning

Tümen¹,

Yıldırım²,

Ergen³

2018

ElAEE

View full text Add to dashboard Cite

To develop effective advanced driving assistance systems, it is important to accurately recognize current driving environments and make critical decisions about driving processes. Preventing accidents through the interaction between the driving assistance systems and the environment and ensuring optimum driving dynamics are the main topics in this field. Vehicles need to recognize the road type and quality at a high accuracy to ensure the most suitable driving for the road type. It is also important to use both uncomplicated and cost-effective systems when performing this detection. In this study, a deep learning-based approach that can be used in vehicle driver assistance systems is proposed to automatically recognize road type and quality. Using this approach, it is possible to determine the road type and the quality of the road using only driving images as the input data. A new convolutional neural network model is designed for classification of the driving images. Driving images obtained from Google Street View are used to evaluate the recognition system for an actual driving environment. The proposed approach shows that the road types were determined with accuracy of 91.41 %, and the pothole road-smooth road distinction was successful at 91.07 %. It can be said that the proposed method is an effective structure that can be used for advanced driving support systems, V2I communications systems, and similar intelligent transportation systems.

show abstract

An Overview of Popular Deep Learning Methods

Abstract: This paper offers an overview of essential concepts in deep learning

Cited by 80 publications

References 38 publications

Recent Innovations in Automated Detection and Classification of Diabetic Retinopathy

Recent Innovations in Automated Detection and Classification of Diabetic Retinopathy

Accelerating Training of Deep Neural Networks on GPU using CUDA

Recognition of Road Type and Quality for Advanced Driver Assistance Systems with Deep Learning

Contact Info

Product

Resources

About