Визначення віку людини за фото на основі нейронних мереж by Євгеній Вербенко, Ольга Мацуга

“…Після навчання VGG-19 та ResNet-50 досягли значень MAE 2.7 та 3.5 відповідно, тоді як Inception-v4 мала значення MAE 3.87. AlexNet продемонстрував значне перенавчання. …”
Get full text

Non-Destructive Estimation of Paper Fiber Using Macro Images: A Comparative Evaluation of Network Architectures and Patch Sizes for Patch-Based Classification by Naoki Kamiya, Kosuke Ashino, Yasuhiro Sakai, Yexin Zhou, Yoichi Ohyanagi, Koji Shibazaki

“…Expanding on studies that implemented EfficientNet-B0, we explore the effectiveness of six other deep learning networks, including DenseNet-201, DarkNet-53, Inception-v3, Xception, Inception-ResNet-v2, and NASNet-Large, in conjunction with enlarged patch sizes. …”
Get full text

Automatic Recognition Method of Letter Images in English Self-Learning Based on Partial Differential Equation Method by Yu Zhao, Shuping Du, Ran Li, Hong Yue

“…Some other layers are added, and some hyperparameters are adjusted when the convolutional neural networks of inception PDEs are constructed by stacking the structure of inception PDEs. …”
Get full text

Reading Modi Lipi: A Deep Learning Journey in Character Recognition by Kanchan Varpe, Sachin Sakhare

“…Utilization of residual networks and inception in image classification has gained popularity in recent times. …”
Get full text

A progressive growing of conditional generative adversarial networks model by Hui MA, Ruiqin WANG, Shuai YANG

“…Progressive growing of generative adversarial networks (PGGAN) is an adversarial network model that can generate high-resolution images.However, when the categories of samples are unbalanced, or the categories of samples are too similar or too dissimilar, it is prone to produce mode collapse, resulting in poor image generation effect.A progressive growing of conditional generative adversarial networks (PGCGAN) model was proposed.The idea of conditional generative adversarial networks (CGAN) was introduced into PGGAN.Using category information as condition, PGGAN was improved in two aspects of network structure and mini-batch standard deviation, and the phenomenon of model collapse in the process of image generation was alleviated.In the experiments on the three data sets, compared with PGGAN, PGCGAN has a greater degree of improvement in inception score and Fréchet inception distance, two evaluation indicators for image generation, and the generated images have higher diversity and authenticity; and PGCGAN multiple unrelated datasets can be trained simultaneously without crashing, and high-quality images can be produced in datasets with imbalanced categories or data that are too similar and dissimilar.…”
Get full text

Perbandingan Arsitektur Convolutional Neural Network Pada Klasifikasi Pneumonia, COVID-19, Lung Opacity, dan Normal Menggunakan Citra Sinar-X Thoraks by Agung Wahyu Setiawan

“…Selain itu, dilakukan perbandingan kinerja sembilan arsitektur CNN, yaitu Inception-ResNet, DenseNet201, InceptionV3, ResNet50v1, ResNet101, ResNet152, ResNet50v2, ResNet101v2, dan ResNet152v2. …”
Get full text

Development of metastasis and survival prediction model of luminal and non-luminal breast cancer with weakly supervised learning based on pathomics by Hui Liu, Linlin Ying, Xing Song, Xueping Xiang, Shumei Wei

“…Result Our results show that the Inception_v3 model shows a particularly robust patch recognition ability for estrogen receptor (ER) recognition. …”
Get full text

Image-Based Arabic Sign Language Recognition System Using Transfer Deep Learning Models by Qanita Bani Baker, Nour Alqudah, Tibra Alsmadi, Rasha Awawdeh

“…These impressive performance measures highlight the distinct capabilities of InceptionV3 in recognizing Arabic characters and underscore its robustness against overfitting. …”
Get full text

Optimizing multi label student performance prediction with GNN-TINet: A contextual multidimensional deep learning framework. by Xiaoyi Zhang, Yakang Zhang, Angelina Lilac Chen, Manning Yu, Lihao Zhang

“…The GNN-TINet utilizes InceptionNet, transformer architectures, and graph neural networks (GNN) to improve precision in multi-label student performance forecasting. …”
Get full text

Optimizing Pretrained Convolutional Neural Networks for Tomato Leaf Disease Detection by Iftikhar Ahmad, Muhammad Hamid, Suhail Yousaf, Syed Tanveer Shah, Muhammad Ovais Ahmad

“…We consider four CNN architectures, namely, VGG-16, VGG-19, ResNet, and Inception V3, and use feature extraction and parameter-tuning to identify and classify tomato leaf diseases. …”
Get full text

Colorectal Malignancy in a Prospective Irish Inflammatory Bowel Disease Population 15 Years Since Diagnosis: Comparison with the EC-IBD Cohort by Mary Shuhaibar, Colm O’Morain

“…As part of the EC-IBD prospective inception cohort study, we had unique opportunity to follow up our patients since diagnosis in the early 1990s. …”
Get full text

NeuroSight: A Deep‐Learning Integrated Efficient Approach to Brain Tumor Detection by Shafayat Bin Shabbir Mugdha, Mahtab Uddin

“…The worst model seemed to be Inception‐v3, with 89.40% test accuracy, 97.89% training accuracy, and 0.4418 validation loss. …”
Get full text

DNA promoter task-oriented dictionary mining and prediction model based on natural language technology by Ruolei Zeng, Zihan Li, Jialu Li, Qingchuan Zhang

“…This BERT-Inception architecture captures information across multiple granularities. …”
Get full text

Brain tumor segmentation by deep learning transfer methods using MRI images by E.Y. Shchetinin

“…Among such models, VGG16, VGG19, Mobilenetv2, Inception, Efficientnetb7, InceptionResnetV2, DenseNet201, DenseNet121 were used. …”
Get full text

A novel carbon emission monitoring method for power generation enterprises based on hybrid transformer model by Yuqiong Jiang, Zhaofang Mao

“…Inspired by them, this paper proposes a novel model, named ICEEMDAN-Inception-Transformer, to thoroughly explore the relationship between power data and carbon emissions, providing precise hourly carbon emission acquisition for power enterprises. …”
Get full text

An Overview of the Florida Bull Test by G. Cliff Lamb

“…Cliff Lamb, describes this test designed as an educational aid for the improvement of beef cattle, its history since inception in 2000, and summarizes the consignors, bulls, breeds, performance, and sale averages of all previous Florida Bull Tests. …”
Get full text

Une revue d’études germaniques à vocation interdisciplinaire et interculturelle by Christine Maillard

“…The contribution offers an overview of the history of the journal Recherches germaniques from its inception in 1971 and shows how the journal’s focus on cultural history and literary studies of German-speaking countries has evolved in the city of Strasbourg, Franco-German and international contexts…”
Get full text

Hyperspectral Image-Based Identification of Maritime Objects Using Convolutional Neural Networks and Classifier Models by Dongmin Seo, Daekyeom Lee, Sekil Park, Sangwoo Oh

“…Among the CNN models, EfficientNet B0 and Inception V3 demonstrated the best performance, with Inception V3 achieving a category-specific accuracy of 97% when weights were excluded. …”
Get full text

Comparison of deep transfer learning models for classification of cervical cancer from pap smear images by Harmanpreet Kaur, Reecha Sharma, Jagroop Kaur

“…A comprehensive comparison of 16 pre-trained models (VGG16, VGG19, ResNet50, ResNet50V2, ResNet101, ResNet101V2, ResNet152, ResNet152V2, DenseNet121, DenseNet169, DenseNet201, MobileNet, XceptionNet, InceptionV3, and InceptionResNetV2) were carried out for cervical cancer classification by relying on the Herlev dataset and Sipakmed dataset. …”
Get full text

Comparison of Deep Learning Techniques in Detection of Sickle Cell Disease. by Mabirizi, Vicent, Kawuma, Simon, Kyarisiima, Addah, Bamutura, David, Atwiine, Barnabas, Nanjebe, Deborah, Oyesigye, Adolf Mukama

“…In our study, we have discovered that Inception V3 yielded the highest accuracy of 97.3% followed by VGG19 at 97.0%, VGG16 at 91%, ResNet50 at 82% and ReNet at 67%, and the CNN-scratch model achieved 81% accuracy. …”
Get full text