Filters








30 Hits in 4.5 sec

Achieving Explainability for Plant Disease Classification with Disentangled Variational Autoencoders [article]

Harshana Habaragamuwa, Yu Oishi, Kenichi Tanaka
2021 arXiv   pre-print
Using the PlantVillage dataset, an acceptable level of explainability was achieved without sacrificing the classification accuracy.  ...  To address this, this paper details the development of a classification and explanation method based on a variational autoencoder (VAE) architecture, which can visualize the variations of the most important  ...  TAKEYA Masaru for his assistance in performing this research. The authors would like to thank the Plant Protection  ... 
arXiv:2102.03082v3 fatcat:w7gunnywvzff3oizpr5x475ak4

Neural Computing [article]

Ayushe Gangal, Peeyush Kumar, Sunita Kumari, Aditya Kumar
2021 arXiv   pre-print
professionals, students and people concerned, by highlighting the work done by major researchers and innovators in this field and thus, encouraging the readers to develop newer and more advanced techniques for  ...  Sparse autoencoder is used for the additional purpose of classification, as it learns features as a byproduct.  ...  This can be achieved by not keeping the encoder and decoder shallow. There are two types of regularized autoencoders, namely, sparse autoencoder and denoising autoencoder.  ... 
arXiv:2107.02744v1 fatcat:kmfb6j3vcrby3mphgzwo6akho4

Explainable Machine Learning for Scientific Insights and Discoveries [article]

Ribana Roscher, Bastian Bohn, Marco F. Duarte, Jochen Garcke
2019 arXiv   pre-print
A prerequisite for obtaining a scientific outcome is domain knowledge, which is needed to gain explainability, but also to enhance scientific consistency.  ...  With respect to these core elements, we provide a survey of recent scientific works incorporating machine learning, and in particular to the way that explainable machine learning is used in their respective  ...  We are grateful for their financial support during the program.  ... 
arXiv:1905.08883v2 fatcat:bwbkmljfljcpboqmppoemari64

Explainable Machine Learning for Scientific Insights and Discoveries

Ribana Roscher, Bastian Bohn, Marco F. Duarte, Jochen Garcke
2020 IEEE Access  
With respect to these core elements, we provide a survey of recent scientific works that incorporate machine learning and the way that explainable machine learning is used in combination with domain knowledge  ...  A prerequisite for obtaining a scientific outcome is domain knowledge, which is needed to gain explainability, but also to enhance scientific consistency.  ...  They would also like to thank the participants of the long term program for fruitful discussions, in particular K. Dow, L. Gao, P. Grandinetti, P. Hähnel, M. Haghighatlari, and R. Jäkel.  ... 
doi:10.1109/access.2020.2976199 fatcat:7wk6ljxlqrdwhpbv7xjk75buk4

Topic Modeling with Wasserstein Autoencoders [article]

Feng Nan, Ran Ding, Ramesh Nallapati, Bing Xiang
2019 arXiv   pre-print
Unlike existing variational autoencoder based models, we directly enforce Dirichlet prior on the latent document-topic vectors.  ...  Together with the widely used coherence measure NPMI, we offer a more wholistic evaluation of topic quality.  ...  More recently, deep neural networks have been successfully used for such probabilistic models with the emergence of variational autoencoders * This work was done when the author was with Amazon.  ... 
arXiv:1907.12374v2 fatcat:gorwfy4lgnfejk54ifu3v2jsoa

Topic Modeling with Wasserstein Autoencoders

Feng Nan, Ran Ding, Ramesh Nallapati, Bing Xiang
2019 Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics  
Unlike existing variational autoencoder based models, we directly enforce Dirichlet prior on the latent document-topic vectors.  ...  Together with the widely used coherence measure NPMI, we offer a more wholistic evaluation of topic quality.  ...  More recently, deep neural networks have been successfully used for such probabilistic models with the emergence of variational autoencoders * This work was done when the author was with Amazon.  ... 
doi:10.18653/v1/p19-1640 dblp:conf/acl/NanDNX19 fatcat:hqanr3yzmfbdvj32jrc5vbr6mu

Explaining the Behavior of Black-Box Prediction Algorithms with Causal Learning [article]

Numair Sani, Daniel Malinsky, Ilya Shpitser
2021 arXiv   pre-print
Specifically, we explore learning the structure of a causal graph where the nodes represent prediction outcomes along with a set of macro-level "interpretable" features, while allowing for arbitrary unmeasured  ...  We propose to explain the behavior of black-box prediction methods (e.g., deep neural networks trained on image pixel data) using causal graphical models.  ...  (An analogous fact may have been more relevant for a plant, which in fact needs water to live.)  ... 
arXiv:2006.02482v3 fatcat:unh73gb2crcitikhtpfqydz2dq

A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challenges [article]

Mohammadreza Salehi, Hossein Mirzaei, Dan Hendrycks, Yixuan Li, Mohammad Hossein Rohban, Mohammad Sabokrou
2021 arXiv   pre-print
The problem has gained significant attention due to its importance for safety deploying models in open-world settings.  ...  Asano for the extremely useful discussions and for reviewing the paper prior to submission.  ...  For instance, a model may be trained on 14 known chest diseases. A new disease, for example, COVID-19, may emerge as unknowns.  ... 
arXiv:2110.14051v1 fatcat:zqfomgebjjb3zl4snmkrojqdny

Learning Neural Textual Representations for Citation Recommendation

Binh Thanh Kieu, Inigo Jauregi Unanue, Son Bao Pham, Hieu Xuan Phan, Massimo Piccardi
2021 2020 25th International Conference on Pattern Recognition (ICPR)  
Plant Disease Identification DAY 2 -Jan 13, 2021 Lin, Yi; Wang, Namin; Ma, Xiaoqing; Li, Ziwei; Bai, Gang 995 How Does DCNN Make Decisions?  ...  Variational Estimates of Mutual Information by Limiting the Critic's Hypothesis Space to RKHS Estimation of Abundance and Distribution of SaltMarsh Plants from Images Using Deep Learning Emerging Relation  ... 
doi:10.1109/icpr48806.2021.9412725 fatcat:3vge2tpd2zf7jcv5btcixnaikm

Deep learning-based clustering approaches for bioinformatics

Md. Rezaul Karim, Oya Deniz Beyan, Achille Zappa, Ivan G. Costa, Dietrich Rebholz-Schuhmann, Michael Cochez, Stefan Josef Decker
2021 Briefings in bioinformatics 22(1)  
He is working towards developing a distributed knowledge pipeline with knowledge graphs and neural networks towards making them explainable and interpretable.  ...  His research interests include machine learning, knowledge graphs, bioinformatics, and explainable artificial intelligence (XAI).  ...  Acknowledgments We gratefully acknowledge the support of the NVIDIA Corporation with the donation of the TITAN Xp GPU for this research.  ... 
doi:10.18154/rwth-conv-243764 fatcat:gpgarkqrbvcmbmn6v75kue6qpi

Deep learning for spatio-temporal forecasting – application to solar energy [article]

Vincent Le Guen
2022 arXiv   pre-print
For video prediction, we introduce the PhyDNet model that disentangles physical dynamics from residual information necessary for prediction, such as texture or details.  ...  Our second direction is to augment incomplete physical models with deep data-driven networks for accurate forecasting.  ...  Gaussian for DeepAR [219] and variants [202, 218] ), or implicitly with a generative model with latent variables (e.g. with conditional variational autoencoders (cVAEs) [292] , conditional generative  ... 
arXiv:2205.03571v1 fatcat:dwkprkwf6ncgjcnvkpx3yrdfjm

Synthetic Data for Deep Learning [article]

Sergey I. Nikolenko
2019 arXiv   pre-print
Third, we turn to privacy-related applications of synthetic data and review the work on generating synthetic datasets with differential privacy guarantees.  ...  for outdoor and urban scenes (autonomous driving), indoor scenes (indoor navigation), aerial navigation, simulation environments for robotics, applications of synthetic data outside computer vision (in  ...  autoencoders (AAE) with variational autoencoders (VAE) for the same problem, with new modifications to the architecture that result in improved generation; • in [457] , Polykovskiy et al. introduced  ... 
arXiv:1909.11512v1 fatcat:qquxnw4dfvgmfeztbpdqhr44gy

Deep learning-based clustering approaches for bioinformatics

2019 Briefings in Bioinformatics  
In this paper, we review state-of-the-art DL-based approaches for cluster analysis that are based on representation learning, which we hope to be useful, particularly for bioinformatics research.  ...  In contrast, deep learning (DL)-based representation and feature learning for clustering have not been reviewed and employed extensively.  ...  Acknowledgments We gratefully acknowledge the support of the NVIDIA Corporation with the donation of the TITAN Xp GPU for this research.  ... 
doi:10.1093/bib/bbz170 pmid:32008043 pmcid:PMC7820885 fatcat:pcqov7ozvvgazdt6icpe4kes6u

A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets [article]

Muhammed Muzammul, Xi Li
2021 arXiv   pre-print
At the end, we showed future directions with existing challenges of the field. In the future, OD methods and models can be analyzed for real-time object detection, tracking strategies.  ...  Furthermore, we explained results with the help of some object detection algorithms, i.e., R-CNN, Fast R-CNN, Faster R-CNN, YOLO, and SSD, which are generally considered the base bone of CV, CNN, and OD  ...  Using EfficientNet architecture, some students performed plant pathology classification with the exploration standard benchmark, i.e.  ... 
arXiv:2107.07927v1 fatcat:pgwxu5tnvzhj7ln3ccndmpilsi

Empowering Things with Intelligence: A Survey of the Progress, Challenges, and Opportunities in Artificial Intelligence of Things [article]

Jing Zhang, Dacheng Tao
2020 arXiv   pre-print
Then, we present progress in AI research for IoT from four perspectives: perceiving, learning, reasoning, and behaving.  ...  In the Internet of Things (IoT) era, billions of sensors and devices collect and process data from the environment, transmit them to cloud centers, and receive feedback via the internet for connectivity  ...  Empowering AIoT with such reasoning abilities is important for making smart and explainable decisions.  ... 
arXiv:2011.08612v1 fatcat:dflut2wdrjb4xojll34c7daol4
« Previous Showing results 1 — 15 out of 30 results