Quantum Convolutional Neural Networks (QCNN) Using Deep Learning for Computer Vision Applications

2021 ◽  
Author(s):  
Varadi Rajesh ◽  
Umesh Parameshwar Naik ◽  
Mohana
Keyword(s):  
Neural Networks ◽  
Computer Vision ◽  
Deep Learning ◽  
Convolutional Neural Networks ◽  
Computer Vision Applications

scholarly journals Image classification using Deep learning

2018 ◽  
Vol 7 (2.7) ◽  
pp. 614 ◽  
Author(s):  
M Manoj krishna ◽  
M Neelima ◽  
M Harshali ◽  
M Venu Gopala Rao
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Image Processing ◽  
Computer Vision ◽  
Deep Learning ◽  
Image Classification ◽  
Convolutional Neural Networks ◽  
Classical Problem

The image classification is a classical problem of image processing, computer vision and machine learning fields. In this paper we study the image classification using deep learning. We use AlexNet architecture with convolutional neural networks for this purpose. Four test images are selected from the ImageNet database for the classification purpose. We cropped the images for various portion areas and conducted experiments. The results show the effectiveness of deep learning based image classification using AlexNet.  

scholarly journals A primer on deep learning and convolutional neural networks for clinicians

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Lara Lloret Iglesias ◽  
Pablo Sanz Bellón ◽  
Amaia Pérez del Barrio ◽  
Pablo Menéndez Fernández-Miranda ◽  
David Rodríguez González ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Networks ◽  
Learning Capabilities ◽  
Computer Vision Applications ◽  
Fully Connected ◽  
Imaging Perspective ◽  
Adaptive Momentum

AbstractDeep learning is nowadays at the forefront of artificial intelligence. More precisely, the use of convolutional neural networks has drastically improved the learning capabilities of computer vision applications, being able to directly consider raw data without any prior feature extraction. Advanced methods in the machine learning field, such as adaptive momentum algorithms or dropout regularization, have dramatically improved the convolutional neural networks predicting ability, outperforming that of conventional fully connected neural networks. This work summarizes, in an intended didactic way, the main aspects of these cutting-edge techniques from a medical imaging perspective.

scholarly journals A Study of The Convolutional Neural Networks Applications

2019 ◽  
Vol 3 (2) ◽  
pp. 31-40 ◽  
Author(s):  
Ahmed Shamsaldin ◽  
Polla Fattah ◽  
Tarik Rashid ◽  
Nawzad Al-Salihi
Keyword(s):  
Neural Networks ◽  
Computer Vision ◽  
Deep Learning ◽  
Natural Language Processing ◽  
Face Recognition ◽  
Convolutional Neural Networks ◽  
Language Processing ◽  
Text Classification ◽  
Scene Labeling ◽  
Real World Problems

At present, deep learning is widely used in a broad range of arenas. A convolutional neural networks (CNN) is becoming the star of deep learning as it gives the best and most precise results when cracking real-world problems. In this work, a brief description of the applications of CNNs in two areas will be presented: First, in computer vision, generally, that is, scene labeling, face recognition, action recognition, and image classification; Second, in natural language processing, that is, the fields of speech recognition and text classification.

scholarly journals Learning Cartographic Building Generalization with Deep Convolutional Neural Networks

2019 ◽  
Vol 8 (6) ◽  
pp. 258 ◽  
Author(s):  
Yu Feng ◽  
Frank Thiemann ◽  
Monika Sester
Keyword(s):  
Neural Networks ◽  
Computer Vision ◽  
Deep Learning ◽  
Convolutional Neural Networks ◽  
Physical Reality ◽  
Learning Approaches ◽  
Deep Convolutional Neural Networks ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Cartographic Generalization

Cartographic generalization is a problem, which poses interesting challenges to automation. Whereas plenty of algorithms have been developed for the different sub-problems of generalization (e.g., simplification, displacement, aggregation), there are still cases, which are not generalized adequately or in a satisfactory way. The main problem is the interplay between different operators. In those cases the human operator is the benchmark, who is able to design an aesthetic and correct representation of the physical reality. Deep learning methods have shown tremendous success for interpretation problems for which algorithmic methods have deficits. A prominent example is the classification and interpretation of images, where deep learning approaches outperform traditional computer vision methods. In both domains-computer vision and cartography-humans are able to produce good solutions. A prerequisite for the application of deep learning is the availability of many representative training examples for the situation to be learned. As this is given in cartography (there are many existing map series), the idea in this paper is to employ deep convolutional neural networks (DCNNs) for cartographic generalizations tasks, especially for the task of building generalization. Three network architectures, namely U-net, residual U-net and generative adversarial network (GAN), are evaluated both quantitatively and qualitatively in this paper. They are compared based on their performance on this task at target map scales 1:10,000, 1:15,000 and 1:25,000, respectively. The results indicate that deep learning models can successfully learn cartographic generalization operations in one single model in an implicit way. The residual U-net outperforms the others and achieved the best generalization performance.

scholarly journals A Training Method for Low Rank Convolutional Neural Networks Based on Alternating Tensor Compose-Decompose Method

2021 ◽  
Vol 11 (2) ◽  
pp. 643
Author(s):  
Sukho Lee ◽  
Hyein Kim ◽  
Byeongseon Jeong ◽  
Jungho Yoon
Keyword(s):  
Neural Networks ◽  
Computer Vision ◽  
Deep Learning ◽  
Convolutional Neural Networks ◽  
Learning Model ◽  
Low Rank ◽  
Training Method ◽  
Training Stage ◽  
Fixed Structure ◽  
Deep Learning Model

Over the past decade, deep learning-based computer vision methods have been shown to surpass previous state-of-the-art computer vision techniques in various fields, and have made great progress in various computer vision problems, including object detection, object segmentation, face recognition, etc. Nowadays, major IT companies are adding new deep-learning-based computer technologies to edge devices such as smartphones. However, since the computational cost of deep learning-based models is still high for edge devices, research is being actively carried out to compress deep learning-based models while not sacrificing high performance. Recently, many lightweight architectures have been proposed for deep learning-based models which are based on low-rank approximation. In this paper, we propose an alternating tensor compose-decompose (ATCD) method for the training of low-rank convolutional neural networks. The proposed training method can better train a compressed low-rank deep learning model than the conventional fixed-structure based training method, so that a compressed deep learning model with higher performance can be obtained in the end of the training. As a representative and exemplary model to which the proposed training method can be applied, we propose a rank-1 convolutional neural network (CNN) which has a structure alternatively containing 3-D rank-1 filters and 1-D filters in the training stage and a 1-D structure in the testing stage. After being trained, the 3-D rank-1 filters can be permanently decomposed into 1-D filters to achieve a fast inference in the test time. The reason that the 1-D filters are not being trained directly in 1-D form in the training stage is that the training of the 3-D rank-1 filters is easier due to the better gradient flow, which makes the training possible even in the case when the fixed structured network with fixed consecutive 1-D filters cannot be trained at all. We also show that the same training method can be applied to the well-known MobileNet architecture so that better parameters can be obtained than with the conventional fixed-structure training method. Furthermore, we show that the 1-D filters in a ResNet like structure can also be trained with the proposed method, which shows the fact that the proposed method can be applied to various structures of networks.

Image Classification Based On CNN: A Survey

2021 ◽  
pp. PP. 18-50
Author(s):  
Ahmed A. Elngar ◽  
◽  
◽  
◽  
◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Neural Networks ◽  
Computer Vision ◽  
Deep Learning ◽  
Image Classification ◽  
Convolutional Neural Networks ◽  
Vision System ◽  
Machine Learning Algorithms ◽  
Traffic Lights

Computer vision is one of the fields of computer science that is one of the most powerful and persuasive types of artificial intelligence. It is similar to the human vision system, as it enables computers to recognize and process objects in pictures and videos in the same way as humans do. Computer vision technology has rapidly evolved in many fields and contributed to solving many problems, as computer vision contributed to self-driving cars, and cars were able to understand their surroundings. The cameras record video from different angles around the car, then a computer vision system gets images from the video, and then processes the images in real-time to find roadside ends, detect other cars, and read traffic lights, pedestrians, and objects. Computer vision also contributed to facial recognition; this technology enables computers to match images of people’s faces to their identities. which these algorithms detect facial features in images and then compare them with databases. Computer vision also play important role in Healthcare, in which algorithms can help automate tasks such as detecting Breast cancer, finding symptoms in x-ray, cancerous moles in skin images, and MRI scans. Computer vision also contributed to many fields such as image classification, object discovery, motion recognition, subject tracking, and medicine. The rapid development of artificial intelligence is making machine learning more important in his field of research. Use algorithms to find out every bit of data and predict the outcome. This has become an important key to unlocking the door to AI. If we had looked to deep learning concept, we find deep learning is a subset of machine learning, algorithms inspired by structure and function of the human brain called artificial neural networks, learn from large amounts of data. Deep learning algorithm perform a task repeatedly, each time tweak it a little to improve the outcome. So, the development of computer vision was due to deep learning. Now we'll take a tour around the convolution neural networks, let us say that convolutional neural networks are one of the most powerful supervised deep learning models (abbreviated as CNN or ConvNet). This name ;convolutional ; is a token from a mathematical linear operation between matrixes called convolution. CNN structure can be used in a variety of real-world problems including, computer vision, image recognition, natural language processing (NLP), anomaly detection, video analysis, drug discovery, recommender systems, health risk assessment, and time-series forecasting. If we look at convolutional neural networks, we see that CNN are similar to normal neural networks, the only difference between CNN and ANN is that CNNs are used in the field of pattern recognition within images mainly. This allows us to encode the features of an image into the structure, making the network more suitable for image-focused tasks, with reducing the parameters required to set-up the model. One of the advantages of CNN that it has an excellent performance in machine learning problems. So, we will use CNN as a classifier for image classification. So, the objective of this paper is that we will talk in detail about image classification in the following sections.

scholarly journals CNN Architectures: Alex Net, Le Net, VGG, Google Net, Res Net

2020 ◽  
Vol 8 (6) ◽  
pp. 953-960 ◽  
Keyword(s):  
Neural Networks ◽  
Computer Vision ◽  
Deep Learning ◽  
Object Recognition ◽  
Speech Recognition ◽  
Object Detection ◽  
Convolutional Neural Networks ◽  
Recognition Pattern

Convolutional Neural Networks(CNNs) are a floating area in Deep Learning. Now a days CNNs are used inside the more note worthy some portion of the Object Recognition tasks. It is used in stand-out utility regions like Speech Recognition, Pattern Acknowledgment, Computer Vision, Object Detection and extraordinary photograph handling programs. CNN orders the realities in light of an opportunity regard. Right now, inside and out assessment of CNN shape and projects are built up. A relative examine of different assortments of CNN are too portrayed on this work.

scholarly journals Towards Edge Computing Using Early-Exit Convolutional Neural Networks

Information ◽  
2021 ◽  
Vol 12 (10) ◽  
pp. 431
Author(s):  
Roberto G. Pacheco ◽  
Kaylani Bochie ◽  
Mateus S. Gilbert ◽  
Rodrigo S. Couto ◽  
Miguel Elias M. Campista
Keyword(s):  
Neural Networks ◽  
Computer Vision ◽  
Convolutional Neural Networks ◽  
Low Latency ◽  
Application Performance ◽  
Early Exit ◽  
Network Load ◽  
Intermediate Layers ◽  
Early Classification ◽  
Computer Vision Applications

In computer vision applications, mobile devices can transfer the inference of Convolutional Neural Networks (CNNs) to the cloud due to their computational restrictions. Nevertheless, besides introducing more network load concerning the cloud, this approach can make unfeasible applications that require low latency. A possible solution is to use CNNs with early exits at the network edge. These CNNs can pre-classify part of the samples in the intermediate layers based on a confidence criterion. Hence, the device sends to the cloud only samples that have not been satisfactorily classified. This work evaluates the performance of these CNNs at the computational edge, considering an object detection application. For this, we employ a MobiletNetV2 with early exits. The experiments show that the early classification can reduce the data load and the inference time without imposing losses to the application performance.

scholarly journals Tox_(R)CNN: Deep Learning-Based Nuclei Profiling tool For Drug Toxicity Screening

2018 ◽  
Author(s):  
Daniel Jimenez-Carretero ◽  
Vahid Abrishami ◽  
Laura Fernández-de-Manuel ◽  
Irene Palacios ◽  
Antonio Quílez-Álvarez ◽  
...  
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Computer Vision ◽  
Deep Learning ◽  
Health Status ◽  
Drug Discovery ◽  
Convolutional Neural Networks ◽  
Cell Assays ◽  
Microscopy Images

AbstractToxicity is an important factor in failed drug development, and its efficient identification and prediction is a major challenge in drug discovery. We have explored the potential of microscopy images of fluorescently labeled nuclei for the prediction of toxicity based on nucleus pattern recognition. Deep learning algorithms obtain abstract representations of images through an automated process, allowing them to efficiently classify complex patterns, and have become the state-of-the art in machine learning for computer vision. Here, deep convolutional neural networks (CNN) were trained to predict toxicity from images of DAPI-stained cells pre-treated with a set of drugs with differing toxicity mechanisms. Different cropping strategies were used for training CNN models, the nuclei-cropping-based Tox-CNN model outperformed other models classifying cells according to health status. Tox-CNN allowed automated extraction of feature maps that clustered compounds according to mechanism of action. Moreover, fully automated region-based CNNs (RCNN) were implemented to detect and classify nuclei, providing per-cell toxicity prediction from raw screening images. We validated both Tox-(R)CNN models for detection of pre-lethal toxicity from nuclei images, which proved to be more sensitive and have broader specificity than established toxicity readouts. These models predicted toxicity of drugs with mechanisms of action other than those they had been trained for and were successfully transferred to other cell assays. The Tox-(R)CNN models thus provide robust, sensitive, and cost-effective tools for in vitro screening of drug-induced toxicity. These models can be adopted for compound prioritization in drug screening campaigns, and could thereby increase the efficiency of drug discovery.Author summaryVisualization of nuclei using different microscopic approaches has for decades allowed the identification of cells undergoing cell death, based on changes in morphology, nuclear density, etc. However, this human-based visual analysis has not been traslated into quantitative tools able to objectively measure cytotoxicity in drug-exposed cells. We asked ourselves if it would be possible to train machines to detect cytotoxicity from microscopy images of fluorescently stained nuclei, without using specific toxicity labeling. Deep learning is the most powerful supervised machine learning methodology available, with exceptional abilities to solve computer vision tasks, and was thus selected for the development of a toxicity quantification tool. Two convolutional neural networks (CNN) were developed to classify cells based on health status: Tox-CNN, relying on prior cell segmentation and cropping of nuclei images, and Tox-RCNN which carries out fully-automated cell detection and classification. Both Tox-(R)CNN classification outputs provided sensitive screening readouts that detected pre-lethal toxicity and were validated for a broad array of toxicity pathways and cell assays. Tox-(R)CNN approaches excel in affordability and applicability to other in vitro toxicity readouts and constitute a robust screening tool for drug discovery.

Sign in / Sign up

Export Citation Format

Share Document