Filters








228 Hits in 5.4 sec

Legal Area Classification: A Comparative Study of Text Classifiers on Singapore Supreme Court Judgments [article]

Jerrold Soh Tsin Howe, Lim How Khang, Ian Ernst Chai
2019 arXiv   pre-print
This paper conducts a comparative study on the performance of various machine learning ("ML") approaches for classifying judgments into legal areas.  ...  few but lengthy documents.  ...  Acknowledgments We thank the anonymous reviewers for their helpful comments and the Singapore Academy of Law for permitting us to scrape and use this corpus.  ... 
arXiv:1904.06470v1 fatcat:lsxuvbkxmjd5ddjdpo44aj4i4i

A Survey on Big Five Personality Traits Prediction Using Tensorflow

Manisha Nilugonda, Dr. Karanam Madhavi, S. Tummala, S. Kosaraju, P. Bobba, S. Singh
2020 E3S Web of Conferences  
This paper provides a survey on detecting of big five personality traits based on facial features recognition using TensorFlow mechanism.  ...  Finally, the graph provides a comparison between various detection of big five personality traits on facial expressions.  ...  of a task using notably smaller datasets than candidates' facial expressions Therefore, we use semi-DL and CNN-based classifieds based on TensorFlow to extend the AVI-AI that can routinely verify communication  ... 
doi:10.1051/e3sconf/202018401053 fatcat:ngc7yh2en5a3fprtkmqimialiq

Automatic Image and Video Caption Generation with Deep Learning: A Concise Review and Algorithmic Overlap

Soheyla Amirian, Khaled Rasheed, Thiab R. Taha, Hamid R. Arabnia
2020 IEEE Access  
GPUs have become the platform of choice for training large, complex Neural Network-based systems because of their ability to accelerate the systems.  ...  , written in Python, and capable of running on top of TensorFlow, CNTK, or Theano.  ... 
doi:10.1109/access.2020.3042484 fatcat:ssl5awoxlrb5rdxbekvv3af74u

Deep learning in generating radiology reports: A survey

Maram Mahmoud A. Monshi, Josiah Poon, Vera Chung
2020 Artificial Intelligence in Medicine  
improving existing DL based models and evaluation metrics.  ...  Generating radiology coherent paragraphs that do more than traditional medical image annotation, or single sentence-based description, has been the subject of recent academic attention.  ...  Using Caffe, [53, 59, 80] acquired pre-trained CNN models on ImageNet for their radiology annotation systems.  ... 
doi:10.1016/j.artmed.2020.101878 pmid:32425358 pmcid:PMC7227610 fatcat:ccy2g2rh2zavdjjvvjlv7poxau

The Application of Artificial Intelligence Decision-Making Algorithm in Crisis Analysis and Optimization of the International Court System

Yuan Zhang, Yuepeng Zhao, Yueqin Zhao, Chia-Huei Wu
2022 Mobile Information Systems  
legal institutions for the construction of smart courts.  ...  Promote the development of the connotation of smart courts through the collaborative integration of artificial intelligence technology and system to promote the deep integration of judicial theory and  ...  Acknowledgments is work was supported by the e Project of Baoding City Science and Technology Bureau (Research on the construction strategy of Baoding grassroots smart court under the background of AI,  ... 
doi:10.1155/2022/8150122 fatcat:mcd56gfxznfprox4zxs5eckywq

A Neural-Network-Based Model of Charge Prediction via the Judicial Interpretation of Crimes

Xinchuan Li, Xiaojun Kang, Chenwei Wang, Lijun Dong, Hong Yao, Shixiang Li
2020 IEEE Access  
(AI) based legal assistant system and made some achievements.  ...  The neural-network-based charge prediction, which is to predict the defendants' charges from the criminal case documents via neural network, has been a development-potential affair in artificial intelligence  ...  According to this idea, the key words are first extracted via the word frequency statistics based on term frequency-inverse document frequency (TF-IDF) [48] , which is employed to evaluate the importance  ... 
doi:10.1109/access.2020.2998108 fatcat:x4df2phukrcqdmufm7gzdb7mba

The Origins and Prevalence of Texture Bias in Convolutional Neural Networks [article]

Katherine L. Hermann, Ting Chen, Simon Kornblith
2020 arXiv   pre-print
We find that, when trained on datasets of images with conflicting shape and texture, CNNs learn to classify by shape at least as easily as by texture.  ...  What factors, then, produce the texture bias in CNNs trained on ImageNet?  ...  Acknowledgments and Disclosure of Funding We thank Jay McClelland, Andrew Lampinen, Akshay Jagadeesh, and Chengxu Zhuang for useful conversations, and Guodong Zhang and Lala Li for comments on an earlier  ... 
arXiv:1911.09071v3 fatcat:b7fkhfftpnearecglfsennxovu

Predicting Institution Outcomes for Inter Partes Review (IPR) Proceedings at the United States Patent Trial & Appeal Board by Deep Learning of Patent Owner Preliminary Response Briefs

Bahrad A. Sokhansanj, Gail L. Rosen
2022 Applied Sciences  
models, and using SHAP for interpretation. (2) Deep learning of document text in context, using convolutional neural networks (CNN) with attention, and comparing LIME and attention visualization for interpretability  ...  The methods are validated on the task of automatically determining case outcomes from unstructured written decision opinions, and then used to predict trial institution or denial based on the patent owner's  ...  Briefs are documents written by attorneys to argue their case on a preliminary issue (generally called a "motion") or for judgment.  ... 
doi:10.3390/app12073656 fatcat:46ximh26hzeull6lgc45lz54bu

Author Profiling in Informal and Formal Language Scenarios Via Transfer Learning

Daniel Escobar-Grisales, Juan Camilo Vásquez-Correa, Juan Rafael Orozco-Arroyave
2021 Tecno Lógicas  
Recognition and identification of traits such as gender, age or location based on text data can help to improve different marketing strategies.  ...  The results indicate that, in relation to the traits considered in this paper, it is possible to transfer the knowledge from a system trained on a specific type of expressions to another one where the  ...  All the authors take responsibility for the integrity of the data and the accuracy of the data analysis.  ... 
doi:10.22430/22565337.2166 fatcat:kcgz5khd25fv3p43543sdyxj7u

PARADE: Passage Representation Aggregation for Document Reranking [article]

Canjia Li, Andrew Yates, Sean MacAvaney, Ben He, Yingfei Sun
2021 arXiv   pre-print
We also conduct efficiency analyses, and highlight several strategies for improving transformer-based aggregation.  ...  Although several approaches for aggregating passage-level signals have been proposed, there has yet to be an extensive comparison of these techniques.  ...  For PARADE-CNN, a FFN with one hidden layer is applied to every CNN representation, and the final score is determined by the sum of those FFN output scores.  ... 
arXiv:2008.09093v2 fatcat:yu4ipuk6sndyjew4j77nzo4wby

RECOGNIZATION AND SYSTEMATIZATION OF MR IMAGES USING FUZZY C-MEANS AND CNN

Samuel Solomon
2022 Zenodo  
One of its applications is the reduction of human judgment in the diagnosis of diseases.Especially, brain tumor diagnosis requires high accuracy, where minute errors in judgment may lead to disaster.  ...  The effect of using separate networks for segmentation of MR images is evaluated by comparing the results with a single network.  ...  This segmentation task requires classifying each voxel as either tumor or nontumor, based on a description of that voxel.  ... 
doi:10.5281/zenodo.7075350 fatcat:3up5u2ut3febrnmwoxvpgwdaee

Neural Multi-Task Learning for Citation Function and Provenance [article]

Xuan Su, Animesh Prasad, Min-Yen Kan, Kazunari Sugiyama
2019 arXiv   pre-print
For both tasks, we show that a single-layer convolutional neural network (CNN) outperforms existing state-of-the-art baselines.  ...  Altogether, our models improve the current state-of-the-arts up to 2\%, with statistical significance for both citation function and provenance prediction tasks.  ...  ., 2018) , most systems used traditional features similar to Low's approach (Low, 2011). These systems show reasonable performance with wide variance.  ... 
arXiv:1811.07351v2 fatcat:q6kwdd4lhjdrpmh46esaoki7vi

A Convolutional Neural Network based Model with Improved Activation Function and Optimizer for Effective Intrusion Detection and Classification

Solaiman Kabir, Sadman Sakib, Md. Akib Hossain, Safi Islam, Muhammad Iqbal Hossain
2021 2021 International Conference on Advance Computing and Innovative Technologies in Engineering (ICACITE)  
It is also a security risk because all of our sensitive and private knowledge on the Internet is exposed to a growing amount of cyber-attacks.  ...  Alongside identification, precise classification of intrusion is of considerable significance for the administrator to take decisive actions.  ...  We want to construct a framework for future implementation to build a fully functional Intrusion Detection System for real-time intrusion detection and classification.  ... 
doi:10.1109/icacite51222.2021.9404584 fatcat:i4ygqvthyndpxfsrbpn2gxexre

2sRanking-CNN: A 2-stage ranking-CNN for diagnosis of glaucoma from fundus images using CAM-extracted ROI as an intermediate input [article]

Tae Joon Jun, Dohyeun Kim, Hoang Minh Nguyen, Daeyoung Kim, Youngsub Eom
2018 arXiv   pre-print
Our results have improved the average accuracy by about 10% over the existing 3-class CNN and ranking-CNN, and especially improved the sensitivity of suspicious class by more than 20% over 3-class CNN.  ...  In addition, the extracted ROI was also found to overlap with the diagnostic criteria of the physician.  ...  Table 1 summarizes the performance evaluation results of 2sRanking-CNN, ranking-CNN, and 3-class CNN based on evaluation metrics.  ... 
arXiv:1805.05727v2 fatcat:qyx3toqvovc2hnsfsa6amanuqe

Automatic recognition of Arabic alphabets sign language using deep learning

Rehab Mustafa Duwairi, Zain Abdullah Halloush
2022 International Journal of Power Electronics and Drive Systems (IJPEDS)  
In this paper, we provide a novel framework for the automatic detection of Arabic sign language, based on transfer learning applied on popular deep learning models for image processing.  ...  As a result, we propose a novel approach for the automatic recognition of Arabic alphabets in sign language based on VGGNet architecture which outperformed the other trained models.  ...  For the future, we intent on working on generating real-time sentences and videos using sign language based on CNN models.  ... 
doi:10.11591/ijece.v12i3.pp2996-3004 fatcat:ayvxbo7m2bc3vhths7p3g6jcbi
« Previous Showing results 1 — 15 out of 228 results