Filters








19 Hits in 7.3 sec

A Review of Recent Deep Learning Approaches in Human-Centered Machine Learning

Tharindu Kaluarachchi, Andrew Reis, Suranga Nanayakkara
2021 Sensors  
Our classification is based on aspects including contribution type, application area, and focused human categories.  ...  Firstly, we collaborated with field domain experts to develop a working definition for HCML.  ...  We also thank Gimhani Pemarathne for their support to proofread and edit. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/s21072514 pmid:33916850 pmcid:PMC8038476 fatcat:wvn3av6e2nf7hdxrswfmyyt2te

Unsupervised Domain Adaptation for Semantic Image Segmentation: a Comprehensive Survey [article]

Gabriela Csurka, Riccardo Volpi, Boris Chidlovskii
2021 arXiv   pre-print
Yet, the state-of-the-art models rely on large amount of annotated samples, which are more expensive to obtain than in tasks such as image classification.  ...  Semantic segmentation plays a fundamental role in a broad variety of computer vision applications, providing key information for the global understanding of an image.  ...  In Sec- of CRFs, which are known for being hard to optimize and tion 2, we present the most widely used SiS models, paying slow at inference time. special attention to deep neural networks, including  ... 
arXiv:2112.03241v1 fatcat:uzlehddvuvfwzf4dfbjimja45e

Artificial Intellgence – Application in Life Sciences and Beyond. The Upper Rhine Artificial Intelligence Symposium UR-AI 2021 [article]

Karl-Herbert Schäfer
2021 arXiv   pre-print
The TriRhenaTech alliance is a network of universities in the Upper-Rhine Trinational Metropolitan Region comprising of the German universities of applied sciences in Furtwangen, Kaiserslautern, Karlsruhe  ...  , Offenburg and Trier, the Baden-Wuerttemberg Cooperative State University Loerrach, the French university network Alsace Tech (comprised of 14 'grandes \'ecoles' in the fields of engineering, architecture  ...  Iraki for helpful comments and discussion.  ... 
arXiv:2112.05657v1 fatcat:wdjgymicyrfybg5zth2dc2i3ni

ICCIT 2020 Conference Proceedings [Front matter]

2020 2020 23rd International Conference on Computer and Information Technology (ICCIT)  
For unsupervised image classification, Convolutional Neural Networks (CNNs) is the state-of-the-art method in the deep learning arena.  ...  Classification of American Sign Language by Applying a Transfer Learned Deep Convolutional Neural Network Md.  ...  We also employed neighborhood benchmarking and multilayer network topology based protein-protein interaction network.  ... 
doi:10.1109/iccit51783.2020.9392749 fatcat:pz3hf7rsmzbjpe6hxjlu5tmrfq

Model Patching: Closing the Subgroup Performance Gap with Data Augmentation [article]

Karan Goel, Albert Gu, Yixuan Li, Christopher Ré
2020 arXiv   pre-print
., exhibiting disparities in skin cancer classification in the presence or absence of a spurious bandage.  ...  To mitigate these performance differences, we introduce model patching, a two-stage framework for improving robustness that encourages the model to be invariant to subgroup differences, and focus on class  ...  Imagenet classification with deep convolutional neural networks. In NIPS, 2012. [47] Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner. Gradient-based learning applied to document recognition.  ... 
arXiv:2008.06775v1 fatcat:swnnihk3nrchri5op6l4rpsuie

MULTIMODAL ANALYSIS: Informed content estimation and audio source separation [article]

Gabriel Meseguer-Brocal
2021 arXiv   pre-print
Our study focuses on the audio and lyrics interaction for targeting source separation and informed content estimation.  ...  Throughout, we focus on the interaction between audio signals and text information.  ...  Currently, deep neural networks are the most popular choice. Table 1 .1 compares both model-agnostic and model-based methods.  ... 
arXiv:2104.13276v3 fatcat:wirjfj4iwjgfteejmeujydey7u

Applications of Deep Neural Networks with Keras [article]

Jeff Heaton
2022 arXiv   pre-print
Deep learning is a group of exciting new technologies for neural networks.  ...  Through a combination of advanced training techniques and neural network architectural components, it is now possible to create neural networks that can handle tabular data, images, text, and audio as  ...  Deep Neural Networks with RMSE We evaluate regression results differently than classification.  ... 
arXiv:2009.05673v5 fatcat:h3jghqylwrbfvfglmwutlfpmay

BabyWalk: Going Farther in Vision-and-Language Navigation by Taking Baby Steps [article]

Wang Zhu, Hexiang Hu, Jiacheng Chen, Zhiwei Deng, Vihan Jain, Eugene Ie, Fei Sha
2020 arXiv   pre-print
In the second phase, the agent uses curriculum-based reinforcement learning to maximize rewards on navigation tasks with increasingly longer instructions.  ...  Learning to follow instructions is of fundamental importance to autonomous agents for vision-and-language navigation (VLN).  ...  Concretely, we first train a convolutional neural network (CNN) based on the visual state features s t to independently predict the existence of landmarks at every time step, then we aggregate the predictions  ... 
arXiv:2005.04625v2 fatcat:sax46ifybnhkjjqh4s2n5uhlte

Big Data for Social Sciences: Measuring patterns of human behavior through large-scale mobile phone data [article]

Pål Sundsøy
2017 arXiv   pre-print
A data-driven and scientific approach to marketing, through more tailored campaigns, contributes to less irrelevant offers for the customers, and better cost efficiency for the companies.  ...  how products spread inside these networks.  ...  Acknowledgement This thesis is based on 7 (out of 21) selected papers related to the analysis of human behaviour using large mobile phone datasets.  ... 
arXiv:1702.08349v1 fatcat:q73dimeqtvdkbpsjjzwed57zqu

3 The Multilingual Brain: Implications for the Future [chapter]

Valéria Csépe, Simone E. Pfenninger, Judit Navracsics
2017 Future Research Directions for Applied Linguistics  
Acknowledgements The authors are grateful for the financial support for this study from the Austrian Science Fund and the Autonomous Province of Bolzano -South Tyrol (Promotion of Educational Policies,  ...  Heuven for his patience in helping establish the distance between the cognates used in the study.  ...  The authors' conclusion and proposal for subnetworks developed in bilinguals was based on a complex network analysis (a graph theoretical approach to examine global and local graph network efficiencies  ... 
doi:10.21832/9781783097135-004 fatcat:mdw4r3hc5be6hdbnaz2elot2le

Natural Language Understanding and Generation for Task-Oriented Dialogue

Bo-Hsiang Tseng, Apollo-University Of Cambridge Repository, William Byrne
2022
The success of deep learning methods has stimulated the rapid development of many NLP research areas.  ...  A tree-based NLG model is proposed and shown to be more easily adapted to unseen domains in comparison to other models.  ...  Deep learning based methods have achieved good performance in classification tasks (Deng et al., 2012; Tur et al., 2012) .  ... 
doi:10.17863/cam.84040 fatcat:4zgqqkubpfab3lb2herfuoboyi

Semi-supervised and weakly-supervised learning with spatio-temporal priors in medical image segmentation

Gabriele Valvano
2021
For this reason, we develop automated methods to reduce the need for collecting high-quality annotated data, both in terms of the number and type of required annotations.  ...  In the thesis, we also open new avenues for future research using AI with limited annotations, which we believe is key to developing robust AI models for medical image analysis.  ...  “Evaluation of a Deep Convolutional Neural Network Method for the Segmentation of Breast Microcalcifications in Mammogra- phy Imaging”.  ... 
doi:10.13118/imtlucca/e-theses/344/ fatcat:qru63k6hibed3pwtxemhd523ua

Abstract of Conferences

2019 Medicine & Health  
To ensure the SCADA system is connected through local area network (LAN) for easier maintenance of system. 2.  ...  Although deep brain stimulation (DBS) is a promising therapy for neuropsychiatric disorders, the potential interactions of DBS and epigenetic changes remain largely unknown.  ... 
doi:10.17576/mh.2019.s1401 fatcat:qtm5gcbzejerxhloaabed2xh54

BabyWalk: Going Farther in Vision-and-Language Navigation by Taking Baby Steps

Wang Zhu, Hexiang Hu, Jiacheng Chen, Zhiwei Deng, Vihan Jain, Eugene Ie, Fei Sha
2020 Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics   unpublished
In the second phase, the agent uses curriculum-based reinforcement learning to maximize rewards on navigation tasks with increasingly longer instructions.  ...  Learning to follow instructions is of fundamental importance to autonomous agents for vision-and-language navigation (VLN).  ...  Concretely, we first train a convolutional neural network (CNN) based on the visual state features s t to independently predict the existence of landmarks at every time step, then we aggregate the predictions  ... 
doi:10.18653/v1/2020.acl-main.229 fatcat:wwjkj6q2lncancnhtcx22y3kiy

Mixed Varieties in Political Language in Egypt: the Presidential Debate between 'Amr Mūsa and 'Abd al-Min'im Abu l-Futūḥ [chapter]

Nina van Kampen
2019 Studies on Arabic Dialectology and Sociolinguistics  
Both my interview assistants and the majority of my participants were recruited through existing networks between students, teachers, and staff at the center, a method which is reflected in the demographics  ...  typology and the relationship between linguistic FoRs, cognitive structures, and neural correlates (O'Keefe 1996) .  ...  The results show that the respondents are aware of the major linguistic boundaries within Egypt, although they did not pay the same attention to all areas: Siwa, the area around Marsa Matruh, the Nile  ... 
doi:10.4000/books.iremam.4895 fatcat:axd726zlf5dfhetj2dzg2ov6zq
« Previous Showing results 1 — 15 out of 19 results