A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Filters
Deep Multi-species Embedding
2017
Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence
Preserved Fulltext
We propose Deep Multi-Species Embedding (DMSE), which jointly embeds vectors corresponding to multiple species as well as vectors representing environmental covariates into a common high-dimensional feature ...
Additionally, we demonstrate the benefit of using a deep neural network to extract features within the embedding and show how they improve the predictive performance of species distribution modelling. ...
We propose a novel method called Deep Multi-Species Embedding which can jointly model the distribution of hundreds of species as well as the correlation among species. ...
doi:10.24963/ijcai.2017/509
dblp:conf/ijcai/ChenXFCG17
fatcat:tvan6q2hnjbjflvzjvz4tmeuiu
Deep Multi-Species Embedding
[article]
2017
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
We propose Deep Multi-Species Embedding (DMSE), which jointly embeds vectors corresponding to multiple species as well as vectors representing environmental covariates into a common high-dimensional feature ...
Additionally, we demonstrate the benefit of using a deep neural network to extract features within the embedding and show how they improve the predictive performance of species distribution modelling. ...
We propose a novel method called Deep Multi-Species Embedding which can jointly model the distribution of hundreds of species as well as the correlation among species. ...
arXiv:1609.09353v4
fatcat:hxj5of3jc5dibaa5i75s4oeheu
Taxonomy and evolution predicting using deep learning in images
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Further, genetic information is implemented to the mushroom image recognition task by using genetic distance embeddings as the representation space for predicting image distance and species identification ...
In this work, a multi-branching recognition framework mediated by genetic information bridges this barrier, which establishes the link between macro-morphology and micro-molecular information of mushrooms ...
(b) Predicting mushroom species through the medium of genetic distance matrix using a multi-perspective framework. (c) Ground truth of genetic distance of 37 species. ...
arXiv:2206.14011v1
fatcat:ceovj2xagrbudiqpgxedqccxlu
Multi-Entity Dependence Learning with Rich Context via Conditional Variational Auto-encoder
[article]
2017
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Our MEDL_CVAE was motivated by two real-world applications in computational sustainability: one studies the spatial correlation among multiple bird species using the eBird data and the other models multi-dimensional ...
Multi-Entity Dependence Learning (MEDL) explores conditional correlations among multiple entities. ...
Recently, Deep Multi-Species Embedding (DMSE) [1] uses a probit model coupled with a deep neural net to capture inter-species correlations. ...
arXiv:1709.05612v1
fatcat:ffwvmjitenfjflrjxq4maobs44
4mCPred-MTL: Accurate Identification of DNA 4mC Sites in Multiple Species Using Multi-Task Deep Learning Based on Multi-Head Attention Mechanism
2021
Frontiers in Cell and Developmental Biology
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
In this predictor, we utilize a multi-task learning framework, in which each task is to train species-specific data based on Transformer. ...
In this study, we proposed a generic 4mC computational predictor, namely, 4mCPred-MTL using multi-task learning coupled with Transformer to predict 4mC sites in multiple species. ...
These words are first randomly initialized and embedded by one-hot embedding, which is referred to as "word embeddings." ...
doi:10.3389/fcell.2021.664669
pmid:34041243
pmcid:PMC8141656
fatcat:zbzsjswk3jgyrjb6g4lmlurbum
Learning Feature Embedding with Strong Neural Activations for Fine-Grained Retrieval
2017
Proceedings of the on Thematic Workshops of ACM Multimedia 2017 - Thematic Workshops '17
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Recently, convolutional neural network (CNN) based deep learning models have achieved promising retrieval performance, as they can learn both feature representations and discriminative distance metrics ...
We present that the novel feature embedding can dramatically enlarge the gap between inter-class variance and intra-class variance, which is the key factor to improve retrieval precision. ...
(Softmax and Triplet)
72.4
67.8
Our Method
Our Feature Embedding
Multi-Task (Softmax and Triplet)
79.3
75.1
Our Method
Our Feature Embedding
Multi-Task (Multi-label Softmax and Triplet) 80.9 ...
doi:10.1145/3126686.3126708
dblp:conf/mm/ShenZJCJCH17
fatcat:w6biffbswvahxakpgcverei37m
Deep Learning for Extreme Multi-label Text Classification
2017
Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval - SIGIR '17
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
However, deep learning has not been explored for XMTC, despite its big successes in other related areas. is paper presents the rst a empt at applying deep learning to XMTC, with a family of new Convolutional ...
Neural Network (CNN) models which are tailored for multi-label classi cation in particular. ...
Speci cally, how can we make deep learning both e ective and scalable when both the feature space and label space are extremely large? ...
doi:10.1145/3077136.3080834
dblp:conf/sigir/LiuCWY17
fatcat:l3igha6dojfgbjmodcjqdkeqsu
Multi-Entity Dependence Learning With Rich Context via Conditional Variational Auto-Encoder
2018
PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Our MEDL_CVAE was motivated by two real-world applications in computational sustainability: one studies the spatial correlation among multiple bird species using the eBird data and the other models multi-dimensional ...
Multi-Entity Dependence Learning (MEDL) explores conditional correlations among multiple entities. ...
Recently, Deep Multi-Species Embedding (DMSE) (Chen et al. 2017 ) uses a probit model coupled with a deep neural net to capture inter-species correlations. ...
doi:10.1609/aaai.v32i1.11335
fatcat:omoixpy74valdjn3sj2r32ttdi
Classification of Underwater Fish Images and Videos via Very Small Convolutional Neural Networks
2022
Journal of Marine Science and Engineering
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
This is especially relevant for fish recognition systems that run unattended on offshore platforms, often on embedded hardware. ...
Here, established deep neural network models would require too many computational resources. ...
species a captured image represents (multi-class classification). ...
doi:10.3390/jmse10060736
fatcat:gw4gom2anbcj5ba5dsdokvtxay
The DKU-LENOVO Systems for the INTERSPEECH 2019 Computational Paralinguistic Challenge
2019
Interspeech 2019
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
For the orca activity detection task, we extract deep embeddings using several deep convolutional neural networks, followed by the Support Vector Machine (SVM) based back end classifier. ...
We also investigate the different ways of fusion for multi-channel input data. ...
It is worth mentioning that the scheme of multi-channel feature-level fusion consumes fewer computational resources than the score-level and embedding-level method which require generating deep embeddings ...
doi:10.21437/interspeech.2019-1386
dblp:conf/interspeech/WuWL19
fatcat:be6cuy6w5bel3ek5wpfivfziq4
Label Hierarchy Transition: Modeling Class Hierarchies to Enhance Deep Classifiers
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
For example, a bird can be categorized according to a three-level hierarchy of order, family, and species. ...
The proposed framework can be adapted to any existing deep network with only minor modifications. ...
We first re-
learn order preserving embedding, which can be embedded visit the traditional multi-task based methods in hierarchical ...
arXiv:2112.02353v1
fatcat:ou25wtcmlfepvcnc6hv4eem7ze
SemiBin: Incorporating information from reference genomes with semi-supervised deep learning leads to better metagenomic assembled genomes (MAGs)
[article]
2021
bioRxiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
SemiBin returns more high-quality bins with larger taxonomic diversity, including more distinct genera and species. ...
This also indicates the better embedding obtained from the deep learning. ...
To show the impact of semi-supervised deep learning, we compared the proposed method to the same pipeline without the deep learning feature embedding step (see Methods). ...
doi:10.1101/2021.08.16.456517
fatcat:3qnnahbu5rg3pegkqe6x7szzqa
Multi-views Embedding for Cattle Re-identification
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
We present various baselines, both based on deep architectures or on standard machine learning algorithms, and compared them with our solution. ...
People re-identification task has seen enormous improvements in the latest years, mainly due to the development of better image features extraction from deep Convolutional Neural Networks (CNN) and the ...
[6] proposed a deep learning technique aiming to automatically identify different wildlife species, as well as counting the occurrences of each species in the image. ...
arXiv:1902.04886v1
fatcat:rtjsdmzn4zd3zg6kybiaolfhrq
Deep Sequential Models for Task Satisfaction Prediction
2017
Proceedings of the 2017 ACM on Conference on Information and Knowledge Management - CIKM '17
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Figure 2 : 2 Neural architecture of the proposed deep Uni ed Multi-view CNN-LSTM model. ...
Speci cally: t = max φ q (q 1 ), φ q (q 2 ), φ q (q 3 ), ..., φ q (q t ) (17) where φ q (q i ) gives the query level satisfaction estimate based on the Multi-View CNN-LSTM architecture. ...
doi:10.1145/3132847.3133001
dblp:conf/cikm/MehrotraASYZKK17
fatcat:xpdyde5u3bazbnw5v6zcf6jitu
Multimodal deep representation learning for protein interaction identification and protein family classification
2019
BMC Bioinformatics
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
The PPI prediction accuracy for eight species ranged from 96.76% to 99.77%, which signifies that our multi-modal deep representation learning framework achieves superior performance compared to other computational ...
To the best of our knowledge, this is the first multi-modal deep representation learning framework for examining the PPI networks. ...
For instance, for S.cerevisiae species, compared to the other four most advanced methods, our multi-modal deep learning predictor still outperforms them. ...
doi:10.1186/s12859-019-3084-y
pmid:31787089
pmcid:PMC6886253
fatcat:pt5nwss7u5h7restbb6ci4r2r4
« Previous
Showing results 1 — 15 out of 53,825 results