| 1. |
- Norlund, Tobias, 1991, et al.
(författare)
-
Transferring Knowledge from Vision to Language: How to Achieve it and how to Measure it?
- 2021
-
Ingår i: Proceedings of the Fourth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP, pp. 149-162, Punta Cana, Dominican Republic. - : Association for Computational Linguistics.
-
Konferensbidrag (refereegranskat)abstract
- Large language models are known to suffer from the hallucination problem in that they are prone to output statements that are false or inconsistent, indicating a lack of knowledge. A proposed solution to this is to provide the model with additional data modalities that complements the knowledge obtained through text. We investigate the use of visual data to complement the knowledge of large language models by proposing a method for evaluating visual knowledge transfer to text for uni- or multimodal language models. The method is based on two steps, 1) a novel task querying for knowledge of memory colors, i.e. typical colors of well-known objects, and 2) filtering of model training data to clearly separate knowledge contributions. Additionally, we introduce a model architecture that involves a visual imagination step and evaluate it with our proposed method. We find that our method can successfully be used to measure visual knowledge transfer capabilities in models and that our novel model architecture shows promising results for leveraging multimodal knowledge in a unimodal setting.
|
|
| 2. |
- Scheuner, Joel, 1991, et al.
(författare)
-
Performance Benchmarking of Infrastructure-as-a-Service (IaaS) Clouds with CloudWorkBench
- 2019
-
Ingår i: ICPE 2019 - Companion of the 2019 ACM/SPEC International Conference on Performance Engineering. - New York, NY, USA : ACM. ; , s. 53-56
-
Konferensbidrag (refereegranskat)abstract
- The continuing growth of the cloud computing market has led to an unprecedented diversity of cloud services with different performance characteristics. To support service selection, researchers and practitioners conduct cloud performance benchmarking by measuring and objectively comparing the performance of different providers and configurations (e.g., instance types in different data center regions). In this tutorial, we demonstrate how to write performance tests for IaaS clouds using the Web-based benchmarking tool Cloud WorkBench (CWB). We will motivate and introduce benchmarking of IaaS cloud in general, demonstrate the execution of a simple benchmark in a public cloud environment, summarize the CWB tool architecture, and interactively develop and deploy a more advanced benchmark together with the participants.
|
|
| 3. |
- Sweidan, Dirar, et al.
(författare)
-
Predicting Customer Churn in Retailing
- 2022
-
Ingår i: Proceedings 21st IEEE International Conference on Machine Learning and Applications ICMLA 2022. - : IEEE. - 9781665462839 - 9781665462846 ; , s. 635-640
-
Konferensbidrag (refereegranskat)abstract
- Customer churn is one of the most challenging problems for digital retailers. With significantly higher costs for acquiring new customers than retaining existing ones, knowledge about which customers are likely to churn becomes essential. This paper reports a case study where a data-driven approach to churn prediction is used for predicting churners and gaining insights about the problem domain. The real-world data set used contains approximately 200 000 customers, describing each customer using more than 50 features. In the pre-processing, exploration, modeling and analysis, attributes related to recency, frequency, and monetary concepts are identified and utilized. In addition, correlations and feature importance are used to discover and understand churn indicators. One important finding is that the churn rate highly depends on the number of previous purchases. In the segment consisting of customers with only one previous purchase, more than 75% will churn, i.e., not make another purchase in the coming year. For customers with at least four previous purchases, the corresponding churn rate is around 25%. Further analysis shows that churning customers in general, and as expected, make smaller purchases and visit the online store less often. In the experimentation, three modeling techniques are evaluated, and the results show that, in particular, Gradient Boosting models can predict churners with relatively high accuracy while obtaining a good balance between precision and recall.
|
|
| 4. |
- Al Sabbagh, Khaled, 1987, et al.
(författare)
-
Improving Data Quality for Regression Test Selection by Reducing Annotation Noise
- 2020
-
Ingår i: Proceedings - 46th Euromicro Conference on Software Engineering and Advanced Applications, SEAA 2020. ; , s. 191-194
-
Konferensbidrag (refereegranskat)abstract
- Big data and machine learning models have been increasingly used to support software engineering processes and practices. One example is the use of machine learning models to improve test case selection in continuous integration. However, one of the challenges in building such models is the identification and reduction of noise that often comes in large data. In this paper, we present a noise reduction approach that deals with the problem of contradictory training entries. We empirically evaluate the effectiveness of the approach in the context of selective regression testing. For this purpose, we use a curated training set as input to a tree-based machine learning ensemble and compare the classification precision, recall, and f-score against a non-curated set. Our study shows that using the noise reduction approach on the training instances gives better results in prediction with an improvement of 37% on precision, 70% on recall, and 59% on f-score.
|
|
| 5. |
- Fredriksson, Teodor, 1992, et al.
(författare)
-
Machine learning models for automatic labeling: A systematic literature review
- 2020
-
Ingår i: ICSOFT 2020 - Proceedings of the 15th International Conference on Software Technologies. - : SCITEPRESS - Science and Technology Publications. ; , s. 552-566
-
Konferensbidrag (refereegranskat)abstract
- Automatic labeling is a type of classification problem. Classification has been studied with the help of statistical methods for a long time. With the explosion of new better computer processing units (CPUs) and graphical processing units (GPUs) the interest in machine learning has grown exponentially and we can use both statistical learning algorithms as well as deep neural networks (DNNs) to solve the classification tasks. Classification is a supervised machine learning problem and there exists a large amount of methodology for performing such task. However, it is very rare in industrial applications that data is fully labeled which is why we need good methodology to obtain error-free labels. The purpose of this paper is to examine the current literature on how to perform labeling using ML, we will compare these models in terms of popularity and on what datatypes they are used on. We performed a systematic literature review of empirical studies for machine learning for labeling. We identified 43 primary studies relevant to our search. From this we were able to determine the most common machine learning models for labeling. Lack of unlabeled instances is a major problem for industry as supervised learning is the most widely used. Obtaining labels is costly in terms of labor and financial costs. Based on our findings in this review we present alternate ways for labeling data for use in supervised learning tasks.
|
|
| 6. |
- Somanath, Sanjay, 1994, et al.
(författare)
-
Towards Urban Digital Twins: A Workflow for Procedural Visualization Using Geospatial Data
- 2024
-
Ingår i: Remote Sensing. - 2072-4292. ; 16:11
-
Tidskriftsartikel (refereegranskat)abstract
- A key feature for urban digital twins (DTs) is an automatically generated detailed 3D representation of the built and unbuilt environment from aerial imagery, footprints, LiDAR, or a fusion of these. Such 3D models have applications in architecture, civil engineering, urban planning, construction, real estate, Geographical Information Systems (GIS), and many other areas. While the visualization of large-scale data in conjunction with the generated 3D models is often a recurring and resource-intensive task, an automated workflow is complex, requiring many steps to achieve a high-quality visualization. Methods for building reconstruction approaches have come a long way, from previously manual approaches to semi-automatic or automatic approaches. This paper aims to complement existing methods of 3D building generation. First, we present a literature review covering different options for procedural context generation and visualization methods, focusing on workflows and data pipelines. Next, we present a semi-automated workflow that extends the building reconstruction pipeline to include procedural context generation using Python and Unreal Engine. Finally, we propose a workflow for integrating various types of large-scale urban analysis data for visualization. We conclude with a series of challenges faced in achieving such pipelines and the limitations of the current approach. However, the steps for a complete, end-to-end solution involve further developing robust systems for building detection, rooftop recognition, and geometry generation and importing and visualizing data in the same 3D environment, highlighting a need for further research and development in this field.
|
|
| 7. |
- Bergström, Gustav, et al.
(författare)
-
Evaluating the layout quality of UML class diagrams using machine learning
- 2022
-
Ingår i: Journal of Systems and Software. - : Elsevier BV. - 0164-1212. ; 192
-
Tidskriftsartikel (refereegranskat)abstract
- UML is the de facto standard notation for graphically representing software. UML diagrams are used in the analysis, construction, and maintenance of software systems. Mostly, UML diagrams capture an abstract view of a (piece of a) software system. A key purpose of UML diagrams is to share knowledge about the system among developers. The quality of the layout of UML diagrams plays a crucial role in their comprehension. In this paper, we present an automated method for evaluating the layout quality of UML class diagrams. We use machine learning based on features extracted from the class diagram images using image processing. Such an automated evaluator has several uses: (1) From an industrial perspective, this tool could be used for automated quality assurance for class diagrams (e.g., as part of a quality monitor integrated into a DevOps toolchain). For example, automated feedback can be generated once a UML diagram is checked in the project repository. (2) In an educational setting, the evaluator can grade the layout aspect of student assignments in courses on software modeling, analysis, and design. (3) In the field of algorithm design for graph layouts, our evaluator can assess the layouts generated by such algorithms. In this way, this evaluator opens up the road for using machine learning to learn good layouting algorithms. Approach.: We use machine learning techniques to build (linear) regression models based on features extracted from the class diagram images using image processing. As ground truth, we use a dataset of 600+ UML Class Diagrams for which experts manually label the quality of the layout. Contributions.: This paper makes the following contributions: (1) We show the feasibility of the automatic evaluation of the layout quality of UML class diagrams. (2) We analyze which features of UML class diagrams are most strongly related to the quality of their layout. (3) We evaluate the performance of our layout evaluator. (4) We offer a dataset of labeled UML class diagrams. In this dataset, we supply for every diagram the following information: (a) a manually established ground truth of the quality of the layout, (b) an automatically established value for the layout-quality of the diagram (produced by our classifier), and (c) the values of key features of the layout of the diagram (obtained by image processing). This dataset can be used for replication of our study and others to build on and improve on this work. Editor's note: Open Science material was validated by the Journal of Systems and Software Open Science Board.
|
|
| 8. |
- Dodig-Crnkovic, Gordana, 1955
(författare)
-
Cognitive Architectures Based on Natural Info-Computation
- 2022
-
Ingår i: Studies in Applied Philosophy, Epistemology and Rational Ethics. - Cham : Springer. - 2192-6255 .- 2192-6263. ; , s. 3-13, s. 3-13
-
Bokkapitel (refereegranskat)abstract
- At the time when the first models of cognitive architectures have been proposed, some forty years ago, understanding of cognition, embodiment and evolution was substantially different from today’s. So was the state of the art of information physics, information chemistry, bioinformatics, neuroinformatics, computational neuroscience, complexity theory, self-organization, theory of evolution, as well as the basic concepts of information and computation. Novel developments support a constructive interdisciplinary framework for cognitive architectures based on natural morphological computing, where interactions between constituents at different levels of organization of matter-energy and their corresponding time-dependent dynamics, lead to complexification of agency and increased cognitive capacities of living organisms that unfold through evolution. Proposed info-computational framework for naturalizing cognition considers present updates (generalizations) of the concepts of information, computation, cognition, and evolution in order to attain an alignment with the current state of the art in corresponding research fields. Some important open questions are suggested for future research with implications for further development of cognitive and intelligent technologies.
|
|
| 9. |
- Fu, Keren, et al.
(författare)
-
Deepside: A general deep framework for salient object detection
- 2019
-
Ingår i: Neurocomputing. - : Elsevier BV. - 0925-2312 .- 1872-8286. ; 356, s. 69-82
-
Tidskriftsartikel (refereegranskat)abstract
- Deep learning-based salient object detection techniques have shown impressive results compared to con- ventional saliency detection by handcrafted features. Integrating hierarchical features of Convolutional Neural Networks (CNN) to achieve fine-grained saliency detection is a current trend, and various deep architectures are proposed by researchers, including “skip-layer” architecture, “top-down” architecture, “short-connection” architecture and so on. While these architectures have achieved progressive improve- ment on detection accuracy, it is still unclear about the underlying distinctions and connections between these schemes. In this paper, we review and draw underlying connections between these architectures, and show that they actually could be unified into a general framework, which simply just has side struc- tures with different depths. Based on the idea of designing deeper side structures for better detection accuracy, we propose a unified framework called Deepside that can be deeply supervised to incorporate hierarchical CNN features. Additionally, to fuse multiple side outputs from the network, we propose a novel fusion technique based on segmentation-based pooling, which severs as a built-in component in the CNN architecture and guarantees more accurate boundary details of detected salient objects. The effectiveness of the proposed Deepside scheme against state-of-the-art models is validated on 8 benchmark datasets.
|
|
| 10. |
- Gerken, Jan, 1991, et al.
(författare)
-
Equivariance versus augmentation for spherical images
- 2022
-
Ingår i: Proceedings of Machine Learning Resaerch. ; , s. 7404-7421
-
Konferensbidrag (refereegranskat)abstract
- We analyze the role of rotational equivariance in convolutional neural networks (CNNs) applied to spherical images. We compare the performance of the group equivariant networks known as S2CNNs and standard non-equivariant CNNs trained with an increasing amount of data augmentation. The chosen architectures can be considered baseline references for the respective design paradigms. Our models are trained and evaluated on single or multiple items from the MNIST- or FashionMNIST dataset projected onto the sphere. For the task of image classification, which is inherently rotationally invariant, we find that by considerably increasing the amount of data augmentation and the size of the networks, it is possible for the standard CNNs to reach at least the same performance as the equivariant network. In contrast, for the inherently equivariant task of semantic segmentation, the non-equivariant networks are consistently outperformed by the equivariant networks with significantly fewer parameters. We also analyze and compare the inference latency and training times of the different networks, enabling detailed tradeoff considerations between equivariant architectures and data augmentation for practical problems.
|
|
