Academic literature on the topic 'CNN embedding networks'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources on the topic 'CNN embedding networks.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Journal articles on the topic "CNN embedding networks"
1
David, Merlin Susan, and Shini Renjith. "Comparison of word embeddings in text classification based on RNN and CNN." IOP Conference Series: Materials Science and Engineering 1187, no. 1 (September 1, 2021): 012029. http://dx.doi.org/10.1088/1757-899x/1187/1/012029.
Full textAbstract:
Abstract This paper presents a comparison of word embeddings in text classification using RNN and CNN. In the field of image classification, deep learning methods like as RNN and CNN have shown to be popular. CNN is most popular model among deep learning techniques in the field of NLP because of its simplicity and parallelism, even if the dataset is huge. Word embedding techniques employed are GloVe and fastText. Use of different word embeddings showed a major difference in the accuracy of the models. When it comes to embedding of rare words, GloVe can sometime perform poorly. Inorder to tackle this issue, fastText method is used. Deep neural networks with fastText showed a remarkable improvement in the accuracy than GloVe. But fastText took some time to train when compared to GloVe. Further, the accuracy was improved by minimizing the batch size. Finally we concluded that the word embeddings have a huge impact on the performance of text classification models
2
Rhanoui, Maryem, Mounia Mikram, Siham Yousfi, and Soukaina Barzali. "A CNN-BiLSTM Model for Document-Level Sentiment Analysis." Machine Learning and Knowledge Extraction 1, no. 3 (July 25, 2019): 832–47. http://dx.doi.org/10.3390/make1030048.
Full textAbstract:
Document-level sentiment analysis is a challenging task given the large size of the text, which leads to an abundance of words and opinions, at times contradictory, in the same document. This analysis is particularly useful in analyzing press articles and blog posts about a particular product or company, and it requires a high concentration, especially when the topic being discussed is sensitive. Nevertheless, most existing models and techniques are designed to process short text from social networks and collaborative platforms. In this paper, we propose a combination of Convolutional Neural Networks (CNN) and Bidirectional Long Short-Term Memory (BiLSTM) models, with Doc2vec embedding, suitable for opinion analysis in long texts. The CNN-BiLSTM model is compared with CNN, LSTM, BiLSTM and CNN-LSTM models with Word2vec/Doc2vec embeddings. The Doc2vec with CNN-BiLSTM model was applied on French newspapers articles and outperformed the other models with 90.66% accuracy.
3
Selvarajah, Jarashanth, and Ruwan Nawarathna. "Identifying Tweets with Personal Medication Intake Mentions using Attentive Character and Localized Context Representations." JUCS - Journal of Universal Computer Science 28, no. 12 (December 28, 2022): 1312–29. http://dx.doi.org/10.3897/jucs.84130.
Full textAbstract:
Individuals with health anomalies often share their experiences on social media sites, such as Twitter, which yields an abundance of data on a global scale. Nowadays, social media data constitutes a leading source to build drug monitoring and surveillance systems. However, a proper assessment of such data requires discarding mentions which do not express drug-related personal health experiences. We automate this process by introducing a novel deep learning model. The model includes character-level and word-level embeddings, embedding-level attention, convolu- tional neural networks (CNN), bidirectional gated recurrent units (BiGRU), and context-aware attentions. An embedding for a word is produced by integrating both word-level and character-level embeddings using an embedding-level attention mechanism, which selects the salient features from both embeddings without expanding dimensionality. The resultant embedding is further analyzed by three CNN layers independently, where each extracts unique n-grams. BiGRUs followed by attention layers further process the outputs from each CNN layer. Besides, the resultant embedding is also encoded by a BiGRU with attention. Our model is developed to cope with the intricate attributes inherent to tweets such as vernacular texts, descriptive medical phrases, frequently misspelt words, abbreviations, short messages, and others. All these four outputs are summed and sent to a softmax classifier. We built a dataset by incorporating tweets from two benchmark datasets designed for the same objective to evaluate the performance. Our model performs substantially better than existing models, including several customized Bidirectional Encoder Representations from Transformers (BERT) models with an F1-score of 0.772.
4
Tang, Weixuan, Bin Li, Shunquan Tan, Mauro Barni, and Jiwu Huang. "CNN-Based Adversarial Embedding for Image Steganography." IEEE Transactions on Information Forensics and Security 14, no. 8 (August 2019): 2074–87. http://dx.doi.org/10.1109/tifs.2019.2891237.
Full text
5
Zheng, Zhedong, Liang Zheng, and Yi Yang. "A Discriminatively Learned CNN Embedding for Person Reidentification." ACM Transactions on Multimedia Computing, Communications, and Applications 14, no. 1 (January 16, 2018): 1–20. http://dx.doi.org/10.1145/3159171.
Full text
6
Wang, Rong, Cong Tian, and Lin Yan. "Malware Detection Using CNN via Word Embedding in Cloud Computing Infrastructure." Scientific Programming 2021 (September 11, 2021): 1–7. http://dx.doi.org/10.1155/2021/8381550.
Full textAbstract:
The Internet of Things (IoT), cloud, and fog computing paradigms provide a powerful large-scale computing infrastructure for a variety of data and computation-intensive applications. These cutting-edge computing infrastructures, however, are nevertheless vulnerable to serious security and privacy risks. One of the most important countermeasures against cybersecurity threats is intrusion detection and prevention systems, which monitor devices, networks, and systems for malicious activity and policy violations. The detection and prevention systems range from antivirus software to hierarchical systems that monitor the traffic of whole backbone networks. At the moment, the primary defensive solutions are based on malware feature extraction. Most known feature extraction algorithms use byte N-gram patterns or binary strings to represent log files or other static information. The information taken from program files is expressed using word embedding (GloVe) and a new feature extraction method proposed in this article. As a result, the relevant vector space model (VSM) will incorporate more information about unknown programs. We utilize convolutional neural network (CNN) to analyze the feature maps represented by word embedding and apply Softmax to fit the probability of a malicious program. Eventually, we consider a program to be malicious if the probability is greater than 0.5; otherwise, it is a benign program. Experimental result shows that our approach achieves a level of accuracy higher than 98%.
7
Liu, Han, Jun Li, Lin He, and Yu Wang. "Superpixel-Guided Layer-Wise Embedding CNN for Remote Sensing Image Classification." Remote Sensing 11, no. 2 (January 17, 2019): 174. http://dx.doi.org/10.3390/rs11020174.
Full textAbstract:
Irregular spatial dependency is one of the major characteristics of remote sensing images, which brings about challenges for classification tasks. Deep supervised models such as convolutional neural networks (CNNs) have shown great capacity for remote sensing image classification. However, they generally require a huge labeled training set for the fine tuning of a deep neural network. To handle the irregular spatial dependency of remote sensing images and mitigate the conflict between limited labeled samples and training demand, we design a superpixel-guided layer-wise embedding CNN (SLE-CNN) for remote sensing image classification, which can efficiently exploit the information from both labeled and unlabeled samples. With the superpixel-guided sampling strategy for unlabeled samples, we can achieve an automatic determination of the neighborhood covering for a spatial dependency system and thus adapting to real scenes of remote sensing images. In the designed network, two types of loss costs are combined for the training of CNN, i.e., supervised cross entropy and unsupervised reconstruction cost on both labeled and unlabeled samples, respectively. Our experimental results are conducted with three types of remote sensing data, including hyperspectral, multispectral, and synthetic aperture radar (SAR) images. The designed SLE-CNN achieves excellent classification performance in all cases with a limited labeled training set, suggesting its good potential for remote sensing image classification.
8
Kim, Jaeyoung, Hanhoon Park, and Jong-Il Park. "CNN-based image steganalysis using additional data embedding." Multimedia Tools and Applications 79, no. 1-2 (October 31, 2019): 1355–72. http://dx.doi.org/10.1007/s11042-019-08251-3.
Full text
9
Li, Yue, Hongqi Wang, Liqun Yu, Sarah Yvonne Cooper, and Jing-Yan Wang. "Query-Specific Deep Embedding of Content-Rich Network." Computational Intelligence and Neuroscience 2020 (August 25, 2020): 1–11. http://dx.doi.org/10.1155/2020/5943798.
Full textAbstract:
In this paper, we propose to embed a content-rich network for the purpose of similarity searching for a query node. In this network, besides the information of the nodes and edges, we also have the content of each node. We use the convolutional neural network (CNN) to represent the content of each node and then use the graph convolutional network (GCN) to further represent the node by merging the representations of its neighboring nodes. The GCN output is further fed to a deep encoder-decoder model to convert each node to a Gaussian distribution and then convert back to its node identity. The dissimilarity between the two nodes is measured by the Wasserstein distance between their Gaussian distributions. We define the nodes of the network to be positives if they are relevant to the query node and negative if they are irrelevant. The labeling of the positives/negatives is based on an upper bound and a lower bound of the Wasserstein distances between the candidate nodes and the query nodes. We learn the parameters of CNN, GCN, encoder-decoder model, Gaussian distributions, and the upper bound and lower bounds jointly. The learning problem is modeled as a minimization problem to minimize the losses of node identification, network structure preservation, positive/negative query-specific relevance-guild distance, and model complexity. An iterative algorithm is developed to solve the minimization problem. We conducted experiments over benchmark networks, especially innovation networks, to verify the effectiveness of the proposed method and showed its advantage over the state-of-the-art methods.
10
Li, Na, Deyun Zhou, Jiao Shi, Mingyang Zhang, Tao Wu, and Maoguo Gong. "Deep Fully Convolutional Embedding Networks for Hyperspectral Images Dimensionality Reduction." Remote Sensing 13, no. 4 (February 15, 2021): 706. http://dx.doi.org/10.3390/rs13040706.
Full textAbstract:
Due to the superior spatial–spectral extraction capability of the convolutional neural network (CNN), CNN shows great potential in dimensionality reduction (DR) of hyperspectral images (HSIs). However, most CNN-based methods are supervised while the class labels of HSIs are limited and difficult to obtain. While a few unsupervised CNN-based methods have been proposed recently, they always focus on data reconstruction and are lacking in the exploration of discriminability which is usually the primary goal of DR. To address these issues, we propose a deep fully convolutional embedding network (DFCEN), which not only considers data reconstruction but also introduces the specific learning task of enhancing feature discriminability. DFCEN has an end-to-end symmetric network structure that is the key for unsupervised learning. Moreover, a novel objective function containing two terms—the reconstruction term and the embedding term of a specific task—is established to supervise the learning of DFCEN towards improving the completeness and discriminability of low-dimensional data. In particular, the specific task is designed to explore and preserve relationships among samples in HSIs. Besides, due to the limited training samples, inherent complexity and the presence of noise in HSIs, a preprocessing where a few noise spectral bands are removed is adopted to improve the effectiveness of unsupervised DFCEN. Experimental results on three well-known hyperspectral datasets and two classifiers illustrate that the low dimensional features of DFCEN are highly separable and DFCEN has promising classification performance compared with other DR methods.
Dissertations / Theses on the topic "CNN embedding networks"
1
Wang, Run Fen. "Semantic Text Matching Using Convolutional Neural Networks." Thesis, Uppsala universitet, Institutionen för lingvistik och filologi, 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-362134.
Full textAbstract:
Semantic text matching is a fundamental task for many applications in NaturalLanguage Processing (NLP). Traditional methods using term frequencyinversedocument frequency (TF-IDF) to match exact words in documentshave one strong drawback which is TF-IDF is unable to capture semanticrelations between closely-related words which will lead to a disappointingmatching result. Neural networks have recently been used for various applicationsin NLP, and achieved state-of-the-art performances on many tasks.Recurrent Neural Networks (RNN) have been tested on text classificationand text matching, but it did not gain any remarkable results, which is dueto RNNs working more effectively on texts with a short length, but longdocuments. In this paper, Convolutional Neural Networks (CNN) will beapplied to match texts in a semantic aspect. It uses word embedding representationsof two texts as inputs to the CNN construction to extract thesemantic features between the two texts and give a score as the output ofhow certain the CNN model is that they match. The results show that aftersome tuning of the parameters the CNN model could produce accuracy,prediction, recall and F1-scores all over 80%. This is a great improvementover the previous TF-IDF results and further improvements could be madeby using dynamic word vectors, better pre-processing of the data, generatelarger and more feature rich data sets and further tuning of the parameters.
2
Hameed, Khurram. "Computer vision based classification of fruits and vegetables for self-checkout at supermarkets." Thesis, Edith Cowan University, Research Online, Perth, Western Australia, 2022. https://ro.ecu.edu.au/theses/2519.
Full textAbstract:
The field of machine learning, and, in particular, methods to improve the capability of machines to perform a wider variety of generalised tasks are among the most rapidly growing research areas in today’s world. The current applications of machine learning and artificial intelligence can be divided into many significant fields namely computer vision, data sciences, real time analytics and Natural Language Processing (NLP). All these applications are being used to help computer based systems to operate more usefully in everyday contexts. Computer vision research is currently active in a wide range of areas such as the development of autonomous vehicles, object recognition, Content Based Image Retrieval (CBIR), image segmentation and terrestrial analysis from space (i.e. crop estimation). Despite significant prior research, the area of object recognition still has many topics to be explored. This PhD thesis focuses on using advanced machine learning approaches to enable the automated recognition of fresh produce (i.e. fruits and vegetables) at supermarket self-checkouts. This type of complex classification task is one of the most recently emerging applications of advanced computer vision approaches and is a productive research topic in this field due to the limited means of representing the features and machine learning techniques for classification. Fruits and vegetables offer significant inter and intra class variance in weight, shape, size, colour and texture which makes the classification challenging.
The applications of effective fruit and vegetable classification have significant importance in daily life e.g. crop estimation, fruit classification, robotic harvesting, fruit quality assessment, etc. One potential application for this fruit and vegetable classification capability is for supermarket self-checkouts. Increasingly, supermarkets are introducing self-checkouts in stores to make the checkout process easier and faster. However, there are a number of challenges with this as all goods cannot readily be sold with packaging and barcodes, for instance loose fresh items (e.g. fruits and vegetables). Adding barcodes to these types of items individually is impractical and pre-packaging limits the freedom of choice when selecting fruits and vegetables and creates additional waste, hence reducing customer satisfaction. The current situation, which relies on customers correctly identifying produce themselves leaves open the potential for incorrect billing either due to inadvertent error, or due to intentional fraudulent misclassification resulting in financial losses for the store. To address this identified problem, the main goals of this PhD work are: (a) exploring the types of visual and non-visual sensors that could be incorporated into a self-checkout system for classification of fruits and vegetables, (b) determining a suitable feature representation method for fresh produce items available at supermarkets, (c) identifying optimal machine learning techniques for classification within this context and (d) evaluating our work relative to the state-of-the-art object classification results presented in the literature.
An in-depth analysis of related computer vision literature and techniques is performed to identify and implement the possible solutions. A progressive process distribution approach is used for this project where the task of computer vision based fruit and vegetables classification is divided into pre-processing and classification techniques. Different classification techniques have been implemented and evaluated as possible solution for this problem. Both visual and non-visual features of fruit and vegetables are exploited to perform the classification. Novel classification techniques have been carefully developed to deal with the complex and highly variant physical features of fruit and vegetables while taking advantages of both visual and non-visual features. The capability of classification techniques is tested in individual and ensemble manner to achieved the higher effectiveness.
Significant results have been obtained where it can be concluded that the fruit and vegetables classification is complex task with many challenges involved. It is also observed that a larger dataset can better comprehend the complex variant features of fruit and vegetables. Complex multidimensional features can be extracted from the larger datasets to generalise on higher number of classes. However, development of a larger multiclass dataset is an expensive and time consuming process. The effectiveness of classification techniques can be significantly improved by subtracting the background occlusions and complexities. It is also worth mentioning that ensemble of simple and less complicated classification techniques can achieve effective results even if applied to less number of features for smaller number of classes. The combination of visual and nonvisual features can reduce the struggle of a classification technique to deal with higher number of classes with similar physical features. Classification of fruit and vegetables with similar physical features (i.e. colour and texture) needs careful estimation and hyper-dimensional embedding of visual features. Implementing rigorous classification penalties as loss function can achieve this goal at the cost of time and computational requirements. There is a significant need to develop larger datasets for different fruit and vegetables related computer vision applications. Considering more sophisticated loss function penalties and discriminative hyper-dimensional features embedding techniques can significantly improve the effectiveness of the classification techniques for the fruit and vegetables applications.
3
Šůstek, Martin. "Word2vec modely s přidanou kontextovou informací." Master's thesis, Vysoké učení technické v Brně. Fakulta informačních technologií, 2017. http://www.nusl.cz/ntk/nusl-363837.
Full textAbstract:
This thesis is concerned with the explanation of the word2vec models. Even though word2vec was introduced recently (2013), many researchers have already tried to extend, understand or at least use the model because it provides surprisingly rich semantic information. This information is encoded in N-dim vector representation and can be recall by performing some operations over the algebra. As an addition, I suggest a model modifications in order to obtain different word representation. To achieve that, I use public picture datasets. This thesis also includes parts dedicated to word2vec extension based on convolution neural network.
4
Gong, Rong. "Automatic assessment of singing voice pronunciation: a case study with Jingju music." Doctoral thesis, Universitat Pompeu Fabra, 2018. http://hdl.handle.net/10803/664421.
Full textAbstract:
Online learning has altered music education remarkable in the last decade. Large and increasing amount of music performing learners participate in online music learning courses due to the easy-accessibility and boundless of time-space constraints.
Singing can be considered the most basic form of music performing. Automatic singing voice assessment, as an important task in Music Information Retrieval (MIR), aims to extract musically meaningful information and measure the quality of learners' singing voice.
Singing correctness and quality is culture-specific and its assessment requires culture-aware methodologies. Jingju (also known as Beijing opera) music is one of the representative music traditions in China and has spread to many places in the world where there are Chinese communities. Our goal is to tackle unexplored automatic singing voice pronunciation assessment problems in jingju music, to make the current eurogeneric assessment approaches more culture-aware, and in return, to develop new assessment approaches which can be generalized to other musical traditions.El aprendizaje en línea ha cambiado notablemente la educación musical en la pasada década. Una cada vez mayor cantidad de estudiantes de interpretación musical participan en cursos de aprendizaje musical en línea por su fácil accesibilidad y no estar limitada por restricciones de tiempo y espacio. Puede considerarse el canto como la forma más básica de interpretación. La evaluación automática de la voz cantada, como tarea importante en la disciplina de Recuperación de Información Musical (MIR por sus siglas en inglés) tiene como objetivo la extracción de información musicalmente significativa y la medición de la calidad de la voz cantada del estudiante. La corrección y calidad del canto son específicas a cada cultura y su evaluación requiere metodologías con especificidad cultural. La música del jingju (también conocido como ópera de Beijing) es una de las tradiciones musicales más representativas de China y se ha difundido a muchos lugares del mundo donde existen comunidades chinas.Nuestro objetivo es abordar problemas aún no explorados sobre la evaluación automática de la voz cantada en la música del jingju, hacer que las propuestas eurogenéticas actuales sobre evaluación sean más específicas culturalmente, y al mismo tiempo, desarrollar nuevas propuestas sobre evaluación que puedan ser generalizables para otras tradiciones musicales.
Books on the topic "CNN embedding networks"
1
Schäfer, Anne, and Rüdiger Schmitt-Beck. A Vicious Circle of Demobilization? Context Effects on Turnout at the 2009 and 2013 German Federal Elections. Oxford University Press, 2017. http://dx.doi.org/10.1093/oso/9780198792130.003.0006.
Full textAbstract:
This chapter explores the contextual effects of constituency-level turnout on individual turnout intentions at the 2009 and 2013 German federal elections. It assesses whether these effects are mediated by citizens’ embedding into networks of political discussants, differentiating between influences originating from discussants inside and those outside of voters’ households. Although we can establish contextual effects, no empirical support is established for their mediation by voters’ discussion networks. Still, we detect relationships between shares of constituency turnout and citizens’ propensity to talk about political matters at all and to do so with other voters. It turns out that political discussants are a very powerful source of environmental influence on electoral behavior. Discussants cohabitating in voters’ households are especially influential. However, embedding into discussion networks is not always a boon; talking to non-voters also has substantial demobilizing effects.
2
Unger, Herwig, and Wolfgang A. Halang, eds. Autonomous Systems 2016. VDI Verlag, 2016. http://dx.doi.org/10.51202/9783186848109.
Full textAbstract:
To meet the expectations raised by the terms Industrie 4.0, Industrial Internet and Internet of Things, real innovations are necessary, which can be brought about by information processing systems working autonomously. Owing to their growing complexity and their embedding in complex environments, their design becomes increasingly critical. Thus, the topics addressed in this book span from verification and validation of safety-related control software and suitable hardware designed for verifiability to be deployed in embedded systems over approaches to suppress electromagnetic interferences to strategies for network routing based on centrality measures and continuous re-authentication in peer-to-peer networks. Methods of neural and evolutionary computing are employed to aid diagnosing retinopathy of prematurity, to invert matrices and to solve non-deterministic polynomial-time hard problems. In natural language processing, interface problems between humans and machines are solved with g...
3
Kubek, Maria M., and Zhong Li, eds. Autonomous Systems 2018. VDI Verlag, 2018. http://dx.doi.org/10.51202/9783186862105.
Full textAbstract:
To meet the expectations raised by the terms Industry 4.0, Industrial Internet and Internet of Things, real innovations are necessary, which can be brought about by information processing systems working autonomously. Owing to their growing complexity and their embedding in ever-changing environments, their design becomes increasingly critical. Thus, the many topics addressed in this book range from data integration on hardware level to methods for security and safety of data and to stochastic methods, data interferences as well as machine learning and search in decentralised systems. Their validity is proven by extensive simulation results. Also, applications for methods from deep learning and neurocomputing are presented. The sustainable management of energy systems using intelligent methods of self-organisation and learning is dealt with in the second major part of this book. As in these particular settings, the assessment of network vulnerabilities plays a crucial role, respective ...
Book chapters on the topic "CNN embedding networks"
1
Pflueger, Maximilian, David J. Tena Cucala, and Egor V. Kostylev. "GNNQ: A Neuro-Symbolic Approach to Query Answering over Incomplete Knowledge Graphs." In The Semantic Web – ISWC 2022, 481–97. Cham: Springer International Publishing, 2022. http://dx.doi.org/10.1007/978-3-031-19433-7_28.
Full textAbstract:
AbstractReal-world knowledge graphs (KGs) are usually incomplete—that is, miss some facts representing valid information. So, when applied to such KGs, standard symbolic query engines fail to produce answers that are expected but not logically entailed by the KGs. To overcome this issue, state-of-the-art ML-based approaches first embed KGs and queries into a low-dimensional vector space, and then produce query answers based on the proximity of the candidate entity and the query embeddings in the embedding space. This allows embedding-based approaches to obtain expected answers that are not logically entailed. However, embedding-based approaches are not applicable in the inductive setting, where KG entities (i.e., constants) seen at runtime may differ from those seen during training. In this paper, we propose a novel neuro-symbolic approach to query answering over incomplete KGs applicable in the inductive setting. Our approach first symbolically augments the input KG with facts representing parts of the KG that match query fragments, and then applies a generalisation of the Relational Graph Convolutional Networks (RGCNs) to the augmented KG to produce the predicted query answers. We formally prove that, under reasonable assumptions, our approach can capture an approach based on vanilla RGCNs (and no KG augmentation) using a (often substantially) smaller number of layers. Finally, we empirically validate our theoretical findings by evaluating an implementation of our approach against the RGCN baseline on several dedicated benchmarks.
2
Barbaglia, Luca, Sergio Consoli, and Sebastiano Manzan. "Exploring the Predictive Power of News and Neural Machine Learning Models for Economic Forecasting." In Mining Data for Financial Applications, 135–49. Cham: Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-66981-2_11.
Full textAbstract:
AbstractForecasting economic and financial variables is a challenging task for several reasons, such as the low signal-to-noise ratio, regime changes, and the effect of volatility among others. A recent trend is to extract information from news as an additional source to forecast economic activity and financial variables. The goal is to evaluate if news can improve forecasts from standard methods that usually are not well-specified and have poor out-of-sample performance. In a currently on-going project, our goal is to combine a richer information set that includes news with a state-of-the-art machine learning model. In particular, we leverage on two recent advances in Data Science, specifically on Word Embedding and Deep Learning models, which have recently attracted extensive attention in many scientific fields. We believe that by combining the two methodologies, effective solutions can be built to improve the prediction accuracy for economic and financial time series. In this preliminary contribution, we provide an overview of the methodology under development and some initial empirical findings. The forecasting model is based on DeepAR, an auto-regressive probabilistic Recurrent Neural Network model, that is combined with GloVe Word Embeddings extracted from economic news. The target variable is the spread between the US 10-Year Treasury Constant Maturity and the 3-Month Treasury Constant Maturity (T10Y3M). The DeepAR model is trained on a large number of related GloVe Word Embedding time series, and employed to produce point and density forecasts.
3
Zhou, Bolei. "Interpreting Generative Adversarial Networks for Interactive Image Generation." In xxAI - Beyond Explainable AI, 167–75. Cham: Springer International Publishing, 2022. http://dx.doi.org/10.1007/978-3-031-04083-2_9.
Full textAbstract:
AbstractSignificant progress has been made by the advances in Generative Adversarial Networks (GANs) for image generation. However, there lacks enough understanding of how a realistic image is generated by the deep representations of GANs from a random vector. This chapter gives a summary of recent works on interpreting deep generative models. The methods are categorized into the supervised, the unsupervised, and the embedding-guided approaches. We will see how the human-understandable concepts that emerge in the learned representation can be identified and used for interactive image generation and editing.
4
Koltai, Júlia, Zoltán Kmetty, and Károly Bozsonyi. "From Durkheim to Machine Learning: Finding the Relevant Sociological Content in Depression and Suicide-Related Social Media Discourses." In Pathways Between Social Science and Computational Social Science, 237–58. Cham: Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-54936-7_11.
Full textAbstract:
AbstractThe phenomenon of suicide has been a focal point since Durkheim among social scientists. Internet and social media sites provide new ways for people to express their positive feelings, but they are also platforms to express suicide ideation or depressed thoughts. Most of these posts are not about real suicide, and some of them are a cry for help. Nevertheless, suicide- and depression-related content varies among platforms, and it is not evident how a researcher can find these materials in mass data of social media. Our paper uses the corpus of more than four million Instagram posts, related to mental health problems. After defining the initial corpus, we present two different strategies to find the relevant sociological content in the noisy environment of social media. The first approach starts with a topic modeling (Latent Dirichlet Allocation), the output of which serves as the basis of a supervised classification method based on advanced machine-learning techniques. The other strategy is built on an artificial neural network-based word embedding language model. Based on our results, the combination of topic modeling and neural network word embedding methods seems to be a promising way to find the research related content in a large digital corpus.Our research can provide added value in the detection of possible self-harm events. With the utilization of complex techniques (such as topic modeling and word embedding methods), it is possible to identify the most problematic posts and most vulnerable users.
5
Xu, Yuemei, Zuwei Fan, and Han Cao. "A Multi-task Text Classification Model Based on Label Embedding Learning." In Communications in Computer and Information Science, 211–25. Singapore: Springer Singapore, 2022. http://dx.doi.org/10.1007/978-981-16-9229-1_13.
Full textAbstract:
AbstractDifferent text classification tasks have specific task features and the performance of text classification algorithm is highly affected by these task-specific features. It is crucial for text classification algorithms to extract task-specific features and thus improve the performance of text classification in different text classification tasks. The existing text classification algorithms use the attention-based neural network models to capture contextualized semantic features while ignores the task-specific features. In this paper, a text classification algorithm based on label-improved attention mechanism is proposed by integrating both contextualized semantic and task-specific features. Through label embedding to learn both word vector and modified-TF-IDF matrix, the task-specific features can be extracted and then attention weights are assigned to different words according to the extracted features, so as to improve the effectiveness of the attention-based neural network models on text classification. Experiments are carried on three text classification task data sets to verify the performance of the proposed method, including a six-category question classification data set, a two-category user comment data set, and a five-category sentiment data set. Results show that the proposed method has an average increase of 3.02% and 5.85% in F1 value compared with the existing LSTMAtt and SelfAtt models.
6
Zhao, Zhangjie, Lin Zhang, Xing Zhang, Ying Wang, and Yi Qin. "CMPD: Context-Based Malicious Parameter Detection for APIs." In Communications in Computer and Information Science, 99–112. Singapore: Springer Nature Singapore, 2022. http://dx.doi.org/10.1007/978-981-19-8285-9_7.
Full textAbstract:
AbstractThe Application Program Interface (API) plays an important role as the channel for data interaction between programs, while the widespread use of APIs has brought security risks that cannot be ignored. The adversary can perform various Web attacks, including SQL Injection and Cross-Site Scripting (XSS), by tampering with the parameters of API. Efficient detection of parameter tampering attacks for API is critical to ensure the system is running in the expected condition, further avoiding data leakage and property loss. Previous works always utilize the rule-based method or simple learning-based method to detect parameter tampering attacks. However, they ignore the contextual information of the API tokens and thus have a poor performance. In this paper, we propose the Context-based Malicious Parameter Detection (CMPD) framework to detect the parameter tampering attacks for APIs. We use a neural network language model to learn the distribution of the parameters, parameter names, and URLs and then use a tree model to detect the malicious query based on the high dimensional API embedding. Experiments show that CMPD outperforms all baseline, including rule-based method, Support Vector Machine (SVM), and Autoencoder, on CSIC 2010 dataset with $$F_1$$ F 1 value reaching 0.971. CMPD can also achieve a 0.895 $$F_1$$ F 1 value when training data is reduced to 20% and can achieve a 0.910 $$F_1$$ F 1 value when negative examples are reduced to 1%.
7
Jain, Gauri, Manisha Sharma, and Basant Agarwal. "Spam Detection on Social Media Using Semantic Convolutional Neural Network." In Deep Learning and Neural Networks, 704–19. IGI Global, 2020. http://dx.doi.org/10.4018/978-1-7998-0414-7.ch039.
Full textAbstract:
This article describes how spam detection in the social media text is becoming increasing important because of the exponential increase in the spam volume over the network. It is challenging, especially in case of text within the limited number of characters. Effective spam detection requires more number of efficient features to be learned. In the current article, the use of a deep learning technology known as a convolutional neural network (CNN) is proposed for spam detection with an added semantic layer on the top of it. The resultant model is known as a semantic convolutional neural network (SCNN). A semantic layer is composed of training the random word vectors with the help of Word2vec to get the semantically enriched word embedding. WordNet and ConceptNet are used to find the word similar to a given word, in case it is missing in the word2vec. The architecture is evaluated on two corpora: SMS Spam dataset (UCI repository) and Twitter dataset (Tweets scrapped from public live tweets). The authors' approach outperforms the-state-of-the-art results with 98.65% accuracy on SMS spam dataset and 94.40% accuracy on Twitter dataset.
8
Rayala, Upendar Rao, and Karthick Seshadri. "Word Embedding Techniques for Sentiment Analyzers." In Advances in Data Mining and Database Management, 233–52. IGI Global, 2021. http://dx.doi.org/10.4018/978-1-7998-8061-5.ch013.
Full textAbstract:
Sentiment analysis is perceived to be a multi-disciplinary research domain composed of machine learning, artificial intelligence, deep learning, image processing, and social networks. Sentiment analysis can be used to determine opinions of the public about products and to find the customers' interest and their feedback through social networks. To perform any natural language processing task, the input text/comments should be represented in a numerical form. Word embeddings represent the given text/sentences/words as a vector that can be employed in performing subsequent natural language processing tasks. In this chapter, the authors discuss different techniques that can improve the performance of sentiment analysis using concepts and techniques like traditional word embeddings, sentiment embeddings, emoticons, lexicons, and neural networks. This chapter also traces the evolution of word embedding techniques with a chronological discussion of the recent research advancements in word embedding techniques.
9
Denecke, Kerstin. "Does Enrichment of Clinical Texts by Ontology Concepts Increases Classification Accuracy?" In MEDINFO 2021: One World, One Health – Global Partnership for Digital Innovation. IOS Press, 2022. http://dx.doi.org/10.3233/shti220148.
Full textAbstract:
In the medical domain, multiple ontologies and terminology systems are available. However, existing classification and prediction algorithms in the clinical domain often ignore or insufficiently utilize semantic information as it is provided in those ontologies. To address this issue, we introduce a concept for augmenting embeddings, the input to deep neural networks, with semantic information retrieved from ontologies. To do this, words and phrases of sentences are mapped to concepts of a medical ontology aggregating synonyms in the same concept. A semantically enriched vector is generated and used for sentence classification. We study our approach on a sentence classification task using a real world dataset which comprises 640 sentences belonging to 22 categories. A deep neural network model is defined with an embedding layer followed by two LSTM layers and two dense layers. Our experiments show, classification accuracy without content enriched embeddings is for some categories higher than without enrichment. We conclude that semantic information from ontologies has potential to provide a useful enrichment of text. Future research will assess to what extent semantic relationships from the ontology can be used for enrichment.
10
Ye, Wei-Cheng, and Jia-Ching Wang. "Multilabel Classification Based on Graph Neural Networks." In Artificial Intelligence. IntechOpen, 2021. http://dx.doi.org/10.5772/intechopen.99681.
Full textAbstract:
Typical Laplacian embedding focuses on building Laplacian matrices prior to minimizing weights of connected graph components. However, for multilabel problems, it is difficult to determine such Laplacian graphs owing to multiple relations between vertices. Unlike typical approaches that require precomputed Laplacian matrices, this chapter presents a new method for automatically constructing Laplacian graphs during Laplacian embedding. By using trace minimization techniques, the topology of the Laplacian graph can be learned from input data, subsequently creating robust Laplacian embedding and influencing graph convolutional networks. Experiments on different open datasets with clean data and Gaussian noise were carried out. The noise level ranged from 6% to 12% of the maximum value of each dataset. Eleven different multilabel classification algorithms were used as the baselines for comparison. To verify the performance, three evaluation metrics specific to multilabel learning are proposed because multilabel learning is much more complicated than traditional single-label settings; each sample can be associated with multiple labels. The experimental results show that the proposed method performed better than the baselines, even when the data were contaminated by noise. The findings indicate that the proposed method is reliably robust against noise.
Conference papers on the topic "CNN embedding networks"
1
Sheikh, Nasrullah, Zekarias T. Kefato, and Alberto Montresor. "Semi-Supervised Heterogeneous Information Network Embedding for Node Classification Using 1D-CNN." In 2018 Fifth International Conference on Social Networks Analysis, Management and Security (SNAMS). IEEE, 2018. http://dx.doi.org/10.1109/snams.2018.8554840.
Full text
2
Jiang, Junjun, Yi Yu, Jinhui Hu, Suhua Tang, and Jiayi Ma. "Deep CNN Denoiser and Multi-layer Neighbor Component Embedding for Face Hallucination." In Twenty-Seventh International Joint Conference on Artificial Intelligence {IJCAI-18}. California: International Joint Conferences on Artificial Intelligence Organization, 2018. http://dx.doi.org/10.24963/ijcai.2018/107.
Full textAbstract:
Most of the current face hallucination methods, whether they are shallow learning-based or deep learning-based, all try to learn a relationship model between Low-Resolution (LR) and High-Resolution (HR) spaces with the help of a training set. They mainly focus on modeling image prior through either model-based optimization or discriminative inference learning. However, when the input LR face is tiny, the learned prior knowledge is no longer effective and their performance will drop sharply. To solve this problem, in this paper we propose a general face hallucination method that can integrate model-based optimization and discriminative inference. In particular, to exploit the model based prior, the Deep Convolutional Neural Networks (CNN) denoiser prior is plugged into the super-resolution optimization model with the aid of image-adaptive Laplacian regularization. Additionally, we further develop a high-frequency details compensation method by dividing the face image to facial components and performing face hallucination in a multi-layer neighbor embedding manner. Experiments demonstrate that the proposed method can achieve promising super-resolution results for tiny input LR faces.
3
Zhang, Yizhou, Guojie Song, Lun Du, Shuwen Yang, and Yilun Jin. "DANE: Domain Adaptive Network Embedding." In Twenty-Eighth International Joint Conference on Artificial Intelligence {IJCAI-19}. California: International Joint Conferences on Artificial Intelligence Organization, 2019. http://dx.doi.org/10.24963/ijcai.2019/606.
Full textAbstract:
Recent works reveal that network embedding techniques enable many machine learning models to handle diverse downstream tasks on graph structured data. However, as previous methods usually focus on learning embeddings for a single network, they can not learn representations transferable on multiple networks. Hence, it is important to design a network embedding algorithm that supports downstream model transferring on different networks, known as domain adaptation. In this paper, we propose a novel Domain Adaptive Network Embedding framework, which applies graph convolutional network to learn transferable embeddings. In DANE, nodes from multiple networks are encoded to vectors via a shared set of learnable parameters so that the vectors share an aligned embedding space. The distribution of embeddings on different networks are further aligned by adversarial learning regularization. In addition, DANE's advantage in learning transferable network embedding can be guaranteed theoretically. Extensive experiments reflect that the proposed framework outperforms other state-of-the-art network embedding baselines in cross-network domain adaptation tasks.
4
Zhao, Gangming, Jingdong Wang, and Zhaoxiang Zhang. "Random Shifting for CNN: a Solution to Reduce Information Loss in Down-Sampling Layers." In Twenty-Sixth International Joint Conference on Artificial Intelligence. California: International Joint Conferences on Artificial Intelligence Organization, 2017. http://dx.doi.org/10.24963/ijcai.2017/486.
Full textAbstract:
Down-sampling is widely adopted in deep convolutional neural networks (DCNN) for reducing the number of network parameters while preserving the transformation invariance. However, it cannot utilize information effectively because it only adopts a fixed stride strategy, which may result in poor generalization ability and information loss. In this paper, we propose a novel random strategy to alleviate these problems by embedding random shifting in the down-sampling layers during the training process. Random shifting can be universally applied to diverse DCNN models to dynamically adjust receptive fields by shifting kernel centers on feature maps in different directions. Thus, it can generate more robust features in networks and further enhance the transformation invariance of down-sampling operators. In addition, random shifting cannot only be integrated in all down-sampling layers including strided convolutional layers and pooling layers, but also improve performance of DCNN with negligible additional computational cost. We evaluate our method in different tasks (e.g., image classification and segmentation) with various network architectures (i.e., AlexNet, FCN and DFN-MR). Experimental results demonstrate the effectiveness of our proposed method.
5
Zhang, Jie, Yuxiao Dong, Yan Wang, Jie Tang, and Ming Ding. "ProNE: Fast and Scalable Network Representation Learning." In Twenty-Eighth International Joint Conference on Artificial Intelligence {IJCAI-19}. California: International Joint Conferences on Artificial Intelligence Organization, 2019. http://dx.doi.org/10.24963/ijcai.2019/594.
Full textAbstract:
Recent advances in network embedding has revolutionized the field of graph and network mining. However, (pre-)training embeddings for very large-scale networks is computationally challenging for most existing methods. In this work, we present ProNE---a fast, scalable, and effective model, whose single-thread version is 10--400x faster than efficient network embedding benchmarks with 20 threads, including LINE, DeepWalk, node2vec, GraRep, and HOPE. As a concrete example, the single-version ProNE requires only 29 hours to embed a network of hundreds of millions of nodes while it takes LINE weeks and DeepWalk months by using 20 threads. To achieve this, ProNE first initializes network embeddings efficiently by formulating the task as sparse matrix factorization. The second step of ProNE is to enhance the embeddings by propagating them in the spectrally modulated space. Extensive experiments on networks of various scales and types demonstrate that ProNE achieves both effectiveness and significant efficiency superiority when compared to the aforementioned baselines. In addition, ProNE's embedding enhancement step can be also generalized for improving other models at speed, e.g., offering >10% relative gains for the used baselines.
6
Dong, Yuxiao, Ziniu Hu, Kuansan Wang, Yizhou Sun, and Jie Tang. "Heterogeneous Network Representation Learning." In Twenty-Ninth International Joint Conference on Artificial Intelligence and Seventeenth Pacific Rim International Conference on Artificial Intelligence {IJCAI-PRICAI-20}. California: International Joint Conferences on Artificial Intelligence Organization, 2020. http://dx.doi.org/10.24963/ijcai.2020/677.
Full textAbstract:
Representation learning has offered a revolutionary learning paradigm for various AI domains. In this survey, we examine and review the problem of representation learning with the focus on heterogeneous networks, which consists of different types of vertices and relations. The goal of this problem is to automatically project objects, most commonly, vertices, in an input heterogeneous network into a latent embedding space such that both the structural and relational properties of the network can be encoded and preserved. The embeddings (representations) can be then used as the features to machine learning algorithms for addressing corresponding network tasks. To learn expressive embeddings, current research developments can fall into two major categories: shallow embedding learning and graph neural networks. After a thorough review of the existing literature, we identify several critical challenges that remain unaddressed and discuss future directions. Finally, we build the Heterogeneous Graph Benchmark to facilitate open research for this rapidly-developing topic.
7
Sun, Yiwei, Suhang Wang, Tsung-Yu Hsieh, Xianfeng Tang, and Vasant Honavar. "MEGAN: A Generative Adversarial Network for Multi-View Network Embedding." In Twenty-Eighth International Joint Conference on Artificial Intelligence {IJCAI-19}. California: International Joint Conferences on Artificial Intelligence Organization, 2019. http://dx.doi.org/10.24963/ijcai.2019/489.
Full textAbstract:
Data from many real-world applications can be naturally represented by multi-view networks where the different views encode different types of relationships (e.g., friendship, shared interests in music, etc.) between real-world individuals or entities. There is an urgent need for methods to obtain low-dimensional, information preserving and typically nonlinear embeddings of such multi-view networks. However, most of the work on multi-view learning focuses on data that lack a network structure, and most of the work on network embeddings has focused primarily on single-view networks. Against this background, we consider the multi-view network representation learning problem, i.e., the problem of constructing low-dimensional information preserving embeddings of multi-view networks. Specifically, we investigate a novel Generative Adversarial Network (GAN) framework for Multi-View Network Embedding, namely MEGAN, aimed at preserving the information from the individual network views, while accounting for connectivity across (and hence complementarity of and correlations between) different views. The results of our experiments on two real-world multi-view data sets show that the embeddings obtained using MEGAN outperform the state-of-the-art methods on node classification, link prediction and visualization tasks.
8
Guo, Junliang, Linli Xu, and Jingchang Liu. "SPINE: Structural Identity Preserved Inductive Network Embedding." In Twenty-Eighth International Joint Conference on Artificial Intelligence {IJCAI-19}. California: International Joint Conferences on Artificial Intelligence Organization, 2019. http://dx.doi.org/10.24963/ijcai.2019/333.
Full textAbstract:
Recent advances in the field of network embedding have shown that low-dimensional network representation is playing a critical role in network analysis. Most existing network embedding methods encode the local proximity of a node, such as the first- and second-order proximities. While being efficient, these methods are short of leveraging the global structural information between nodes distant from each other. In addition, most existing methods learn embeddings on one single fixed network, and thus cannot be generalized to unseen nodes or networks without retraining. In this paper we present SPINE, a method that can jointly capture the local proximity and proximities at any distance, while being inductive to efficiently deal with unseen nodes or networks. Extensive experimental results on benchmark datasets demonstrate the superiority of the proposed framework over the state of the art.
9
Chan, Patrick P. K., Xian Hu, Lili Zhao, Daniel S. Yeung, Dapeng Liu, and Lei Xiao. "Convolutional Neural Networks based Click-Through Rate Prediction with Multiple Feature Sequences." In Twenty-Seventh International Joint Conference on Artificial Intelligence {IJCAI-18}. California: International Joint Conferences on Artificial Intelligence Organization, 2018. http://dx.doi.org/10.24963/ijcai.2018/277.
Full textAbstract:
Convolutional Neural Network (CNN) achieved satisfying performance in click-through rate (CTR) prediction in recent studies. Since features used in CTR prediction have no meaningful sequence in nature, the features can be arranged in any order. As CNN learns the local information of a sample, the feature sequence may influence its performance significantly. However, this problem has not been fully investigated. This paper firstly investigates whether and how the feature sequence affects the performance of the CNN-based CTR prediction method. As the data distribution of CTR prediction changes with time, the best current sequence may not be suitable for future data. Two multi-sequence models are proposed to learn the information provided by different sequences. The first model learns all sequences using a single feature learning module, while each sequence is learnt individually by a feature learning module in the second one. Moreover, a method of generating a set of embedding sequences which aims to consider the combined influence of all feature pairs on feature learning is also introduced. The experiments are conducted to demonstrate the effectiveness and stability of our proposed models in the offline and online environment on both the benchmark Avazu dataset and a real commercial dataset.
10
do Carmo, P., I. J. Reis Filho, and R. Marcacini. "Commodities trend link prediction on heterogeneous information networks." In Symposium on Knowledge Discovery, Mining and Learning. Sociedade Brasileira de Computação - SBC, 2021. http://dx.doi.org/10.5753/kdmile.2021.17464.
Full textAbstract:
Events can be defined as an action or a series of actions that have a determined theme, time, and place. Event analysis tasks for knowledge extraction from news and social media have been explored in recent years. However, there are still few studies that aim to enrich predictive models using event data. In particular, agribusiness events have multiple components to be considered for a successful prediction model. For example, price trend predictions for commodities can be performed through time series analysis of prices, but we can also consider events that represent knowledge about external factors during the training step of predictive models. In this paper, we present a method for integrating events into trend prediction tasks. First, we propose to model events and time-series information through heterogeneous information networks (HIN) that allow multiple components to be directly modeled through multi-type nodes and edges. Second, we learn features from HIN through network embedding methods, i.e., network nodes are mapped to a dense vector of features. In particular, we propose a network embedding method that propagates the semantic of the pre-trained neural language models to a heterogeneous information network and evaluates its performance in a trend link prediction. We show that the use of our proposed model language-based embedding propagation is competitive with state-of-art network embeddings algorithms. Moreover, our proposal performs network embedding incrementally, thereby allowing new events to be inserted in the same semantic space without rebuilding the entire network embedding.
Reports on the topic "CNN embedding networks"
1
Bano, Masooda, and Zeena Oberoi. Embedding Innovation in State Systems: Lessons from Pratham in India. Research on Improving Systems of Education (RISE), December 2020. http://dx.doi.org/10.35489/bsg-rise-wp_2020/058.
Full textAbstract:
The learning crisis in many developing countries has led to searches for innovative teaching models. Adoption of innovation, however, disrupts routine and breaks institutional inertia, requiring government employees to change their way of working. Introducing and embedding innovative methods for improving learning outcomes within state institutions is thus a major challenge. For NGO-led innovation to have largescale impact, we need to understand: (1) what factors facilitate its adoption by senior bureaucracy and political elites; and (2) how to incentivise district-level field staff and school principals and teachers, who have to change their ways of working, to implement the innovation? This paper presents an ethnographic study of Pratham, one of the most influential NGOs in the domain of education in India today, which has attracted growing attention for introducing an innovative teaching methodology— Teaching at the Right Level (TaRL) – with evidence of improved learning outcomes among primary-school students and adoption by a number of states in India. The case study suggests that while a combination of factors, including evidence of success, ease of method, the presence of a committed bureaucrat, and political opportunity are key to state adoption of an innovation, exposure to ground realities, hand holding and confidence building, informal interactions, provision of new teaching resources, and using existing lines of communication are core to ensuring the co-operation of those responsible for actual implementation. The Pratham case, however, also confirms existing concerns that even when NGO-led innovations are successfully implemented at a large scale, their replication across the state and their sustainability remain a challenge. Embedding good practice takes time; the political commitment leading to adoption of an innovation is often, however, tied to an immediate political opportunity being exploited by the political elites. Thus, when political opportunity rather than a genuine political will creates space for adoption of an innovation, state support for that innovation fades away before the new ways of working can replace the old habits. In contexts where states lack political will to improve learning outcomes, NGOs can only hope to make systematic change in state systems if, as in the case of Pratham, they operate as semi-social movements with large cadres of volunteers. The network of volunteers enables them to slow down and pick up again in response to changing political contexts, instead of quitting when state actors withdraw. Involving the community itself does not automatically lead to greater political accountability. Time-bound donor-funded NGO projects aiming to introduce innovation, however large in scale, simply cannot succeed in bringing about systematic change, because embedding change in state institutions lacking political will requires years of sustained engagement.
2
Kelly, Luke. Lessons Learned on Cultural Heritage Protection in Conflict and Protracted Crisis. Institute of Development Studies (IDS), April 2021. http://dx.doi.org/10.19088/k4d.2021.068.
Full textAbstract:
This rapid review examines evidence on the lessons learned from initiatives aimed at embedding better understanding of cultural heritage protection within international monitoring, reporting and response efforts in conflict and protracted crisis. The report uses the terms cultural property and cultural heritage interchangeably. Since the signing of the Hague Treaty in 1954, there has bee a shift from 'cultural property' to 'cultural heritage'. Culture is seen less as 'property' and more in terms of 'ways of life'. However, in much of the literature and for the purposes of this review, cultural property and cultural heritage are used interchangeably. Tangible and intangible cultural heritage incorporates many things, from buildings of globally recognised aesthetic and historic value to places or practices important to a particular community or group. Heritage protection can be supported through a number of frameworks international humanitarian law, human rights law, and peacebuilding, in addition to being supported through networks of the cultural and heritage professions. The report briefly outlines some of the main international legal instruments and approaches involved in cultural heritage protection in section 2. Cultural heritage protection is carried out by national cultural heritage professionals, international bodies and non-governmental organisations (NGOs) as well as citizens. States and intergovernmental organisations may support cultural heritage protection, either bilaterally or by supporting international organisations. The armed forces may also include the protection of cultural heritage in some operations in line with their obligations under international law. In the third section, this report outlines broad lessons on the institutional capacity and politics underpinning cultural protection work (e.g. the strength of legal protections; institutional mandates; production and deployment of knowledge; networks of interested parties); the different approaches were taken; the efficacy of different approaches; and the interface between international and local approaches to heritage protection.