Статті в журналах: "Geometric learning"

1

Omohundro, Stephen M. "Geometric learning algorithms." Physica D: Nonlinear Phenomena 42, no. 1-3 (June 1990): 307–21. http://dx.doi.org/10.1016/0167-2789(90)90085-4.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

2

Jamshidi, Arta, Michael Kirby, and Dave Broomhead. "Geometric Manifold Learning." IEEE Signal Processing Magazine 28, no. 2 (March 2011): 69–76. http://dx.doi.org/10.1109/msp.2010.939550.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

3

Gong, Wenjuan, Bin Zhang, Chaoqi Wang, Hanbing Yue, Chuantao Li, Linjie Xing, Yu Qiao, Weishan Zhang, and Faming Gong. "A Literature Review: Geometric Methods and Their Applications in Human-Related Analysis." Sensors 19, no. 12 (June 23, 2019): 2809. http://dx.doi.org/10.3390/s19122809.

Повний текст джерела

Анотація:

Geometric features, such as the topological and manifold properties, are utilized to extract geometric properties. Geometric methods that exploit the applications of geometrics, e.g., geometric features, are widely used in computer graphics and computer vision problems. This review presents a literature review on geometric concepts, geometric methods, and their applications in human-related analysis, e.g., human shape analysis, human pose analysis, and human action analysis. This review proposes to categorize geometric methods based on the scope of the geometric properties that are extracted: object-oriented geometric methods, feature-oriented geometric methods, and routine-based geometric methods. Considering the broad applications of deep learning methods, this review also studies geometric deep learning, which has recently become a popular topic of research. Validation datasets are collected, and method performances are collected and compared. Finally, research trends and possible research topics are discussed.

Стилі APA, Harvard, Vancouver, ISO та ін.

4

Gao, Huiping, and Zhongchen Ma. "Geometric Metric Learning for Multi-Output Learning." Mathematics 10, no. 10 (May 11, 2022): 1632. http://dx.doi.org/10.3390/math10101632.

Повний текст джерела

Анотація:

Due to its wide applications, multi-output learning that predicts multiple output values for a single input at the same time is becoming more and more attractive. As one of the most popular frameworks for dealing with multi-output learning, the performance of the k-nearest neighbor (kNN) algorithm mainly depends on the metric used to compute the distance between different instances. In this paper, we propose a novel cost-weighted geometric mean metric learning method for multi-output learning. Specifically, this method learns a geometric mean metric which can make the distance between the input embedding and its correct output be smaller than the distance between the input embedding and the outputs of its nearest neighbors. The learned geometric mean metric can discover output dependencies and move the instances with different outputs far away in the embedding space. In addition, our objective function has a closed solution, and thus the calculation speed is very fast. Compared with state-of-the-art methods, it is easier to explain and also has a faster calculation speed. Experiments conducted on two multi-output learning tasks (i.e., multi-label classification and multi-objective regression) have confirmed that our method provides better results than state-of-the-art methods.

Стилі APA, Harvard, Vancouver, ISO та ін.

5

Gao, Xiaoqing, and Hugh R. Wilson. "Implicit learning of geometric eigenfaces." Vision Research 99 (June 2014): 12–18. http://dx.doi.org/10.1016/j.visres.2013.07.015.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

6

Goldman, Sally A., Stephen S. Kwek, and Stephen D. Scott. "Agnostic Learning of Geometric Patterns." Journal of Computer and System Sciences 62, no. 1 (February 2001): 123–51. http://dx.doi.org/10.1006/jcss.2000.1723.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

7

Feng, Zixin, Teligeng Yun, Yu Zhou, Ruirui Zheng, and Jianjun He. "Kernel Geometric Mean Metric Learning." Applied Sciences 13, no. 21 (November 6, 2023): 12047. http://dx.doi.org/10.3390/app132112047.

Повний текст джерела

Анотація:

Geometric mean metric learning (GMML) algorithm is a novel metric learning approach proposed recently. It has many advantages such as unconstrained convex objective function, closed form solution, faster computational speed, and interpretability over other existing metric learning technologies. However, addressing the nonlinear problem is not effective enough. The kernel method is an effective method to solve nonlinear problems. Therefore, a kernel geometric mean metric learning (KGMML) algorithm is proposed. The basic idea is to transform the input space into a high-dimensional feature space through nonlinear transformation, and use the integral representation of the weighted geometric mean and the Woodbury matrix identity in new feature space to generalize the analytical solution obtained in the GMML algorithm as a form represented by a kernel matrix, and then the KGMML algorithm is obtained through operations. Experimental results on 15 datasets show that the proposed algorithm can effectively improve the accuracy of the GMML algorithm and other metric algorithms.

Стилі APA, Harvard, Vancouver, ISO та ін.

8

AKARSU, Murat. "Understanding of Geometric Reflection: John’s learning path for geometric reflection." Kuramsal Eğitimbilim 15, no. 1 (January 31, 2022): 64–89. http://dx.doi.org/10.30831/akukeg.952022.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

9

Townshend, Raphael, Ligia Melo, David Liu, and Ron O. Dror. "Geometric Deep Learning on Biomolecular Structure." Biophysical Journal 120, no. 3 (February 2021): 290a. http://dx.doi.org/10.1016/j.bpj.2020.11.1863.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

10

Kaplan, Haim, Yishay Mansour, Yossi Matias, and Uri Stemmer. "Differentially Private Learning of Geometric Concepts." SIAM Journal on Computing 51, no. 4 (July 7, 2022): 952–74. http://dx.doi.org/10.1137/21m1406428.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

11

Atz, Kenneth, Francesca Grisoni, and Gisbert Schneider. "Geometric deep learning on molecular representations." Nature Machine Intelligence 3, no. 12 (December 2021): 1023–32. http://dx.doi.org/10.1038/s42256-021-00418-8.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

12

Townshend, Raphael J. L., Stephan Eismann, Andrew M. Watkins, Ramya Rangan, Maria Karelina, Rhiju Das, and Ron O. Dror. "Geometric deep learning of RNA structure." Science 373, no. 6558 (August 27, 2021): 1047–51. http://dx.doi.org/10.1126/science.abe5650.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

13

Lu, Qingkai, Yifan Zhu, and Liangjun Zhang. "Excavation Reinforcement Learning Using Geometric Representation." IEEE Robotics and Automation Letters 7, no. 2 (April 2022): 4472–79. http://dx.doi.org/10.1109/lra.2022.3150511.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

14

Greengard, Samuel. "Geometric deep learning advances data science." Communications of the ACM 64, no. 1 (January 2021): 13–15. http://dx.doi.org/10.1145/3433951.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

15

Bshouty, Nader H., Paul W. Goldberg, Sally A. Goldman, and H. David Mathias. "Exact Learning of Discretized Geometric Concepts." SIAM Journal on Computing 28, no. 2 (January 1998): 674–99. http://dx.doi.org/10.1137/s0097539794274246.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

16

Jung, Hong-Gyu, and Seong-Whan Lee. "Few-Shot Learning With Geometric Constraints." IEEE Transactions on Neural Networks and Learning Systems 31, no. 11 (November 2020): 4660–72. http://dx.doi.org/10.1109/tnnls.2019.2957187.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

17

Du, Dawei, Honggang Qi, Longyin Wen, Qi Tian, Qingming Huang, and Siwei Lyu. "Geometric Hypergraph Learning for Visual Tracking." IEEE Transactions on Cybernetics 47, no. 12 (December 2017): 4182–95. http://dx.doi.org/10.1109/tcyb.2016.2626275.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

18

Lei, Na, Dongsheng An, Yang Guo, Kehua Su, Shixia Liu, Zhongxuan Luo, Shing-Tung Yau, and Xianfeng Gu. "A Geometric Understanding of Deep Learning." Engineering 6, no. 3 (March 2020): 361–74. http://dx.doi.org/10.1016/j.eng.2019.09.010.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

19

Fife, James H., Kofi James, and Malcolm Bauer. "A Learning Progression for Geometric Transformations." ETS Research Report Series 2019, no. 1 (January 28, 2019): 1–16. http://dx.doi.org/10.1002/ets2.12236.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

20

Gopal, Тadepalli. "Learning Computational Logic through Geometric Reasoning." Innovative STEM Education 5, no. 1 (July 24, 2023): 7–12. http://dx.doi.org/10.55630/stem.2023.0501.

Повний текст джерела

Анотація:

Computers control everyday things ranging from the heart pacemakers to voice controlled devices that form an integral part of many appliances. Failures related to computers regularly cause disruption, damage and occasionally death. Computational logic establishes the facts in a logical formalism. It attempts to understand the nature of mathematical reasoning with a wide variety of formalisms, techniques and technologies. Formal verification uses mathematical and logical formalisms to prove the correctness of designs. Formal methods provide the maturity and agility to assimilate the future concepts, languages, techniques and tools for computational methods and models. The quest for simplification of formal verification is never ending. This summary report advocates the use of geometry to construct quick conclusions by the human mind that can be formally verified if necessary.

Стилі APA, Harvard, Vancouver, ISO та ін.

21

Zhao, Peng, Tao Wu, Shiyi Zhao, and Huiting Liu. "Robust transfer learning based on Geometric Mean Metric Learning." Knowledge-Based Systems 227 (September 2021): 107227. http://dx.doi.org/10.1016/j.knosys.2021.107227.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

22

Riswandha, Septian Henry, Budi Usodo, and Riyadi Riyadi. "Experimentation of Transformative Learning and Realistic Mathematic Education Learning Models on Mathematics Learning Achievement." QALAMUNA: Jurnal Pendidikan, Sosial, dan Agama 15, no. 1 (June 29, 2023): 713–22. http://dx.doi.org/10.37680/qalamuna.v15i1.4260.

Повний текст джерела

Анотація:

The research aims to investigate and evaluate the efficacy of different learning models on mathematics learning outcomes, specifically focusing on the students' van Hiele geometric reasoning capacity. The study employed a quasi-experimental design. The practice is carried out in Public Junior High Schools in Sukoharjo Regency, part of the Central Java Province in Indonesia. The utilized learning models were transformative learning, actual mathematics education, and direct instruction. The study encompassed a total of 281 individuals, who were selected from 9 classes across three distinct institutions. Data analysis is conducted with a two-way analysis of variance (ANOVA) approach. The research findings indicate that (1) the learning model has a positive and significant impact on mathematics learning outcomes; (2) the van Hiele level of geometric thinking ability has a positive and significant influence on mathematics learning outcomes; (3) there is a positive and significant interaction between learning models and van Hiele level of geometric thinking ability on mathematics learning outcomes; and (4) among the transformative learning, Real Mathematics Education, and Direct Instruction models, the transformative learning model yields the best mathematics learning outcomes.

Стилі APA, Harvard, Vancouver, ISO та ін.

23

Bell, Clare V. "Learning Geometric Concepts through Ceramic Tile Design." Mathematics Teaching in the Middle School 9, no. 3 (November 2003): 134–40. http://dx.doi.org/10.5951/mtms.9.3.0134.

Повний текст джерела

Анотація:

Symmetry and geometric patterns are commonly used in the creation of designs that symbolize and contribute to the definition of culture. Native American weaving and pottery designs, Mexican tiles, and Islamic religious art are forms of cultural representation that rely heavily on a repetition of geometric figures and symmetry. These items are used as examples of geometric art for the lessons in this article (see fig. 1).

Стилі APA, Harvard, Vancouver, ISO та ін.

24

Barnabò, Giorgio, Federico Siciliano, Carlos Castillo, Stefano Leonardi, Preslav Nakov, Giovanni Da San Martino, and Fabrizio Silvestri. "Deep active learning for misinformation detection using geometric deep learning." Online Social Networks and Media 33 (January 2023): 100244. http://dx.doi.org/10.1016/j.osnem.2023.100244.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

25

Sudarwan, Robert Edy, and Heri Retnawati. "PENGEMBANGAN PERANGKAT ASSESSMENT PEMBELAJARAN MATEMATIKA POKOK BAHASAN GEOMETRI DAN PENGUKURAN SMP/MTs." Jurnal Riset Pendidikan Matematika 2, no. 2 (November 2, 2015): 251. http://dx.doi.org/10.21831/jrpm.v2i2.7344.

Повний текст джерела

Анотація:

Penelitian ini bertujuan untuk: (1) mengembangkan produk perangkat assessment pembelajaran pada pokok bahasan geometri dan pengukuran yang berorientasi pada aspek pengetahuan, keterampilan dan sikap peserta didik SMP/MTs kelas VII dan VIII sebagai hasil pengembangan berdasarkan kajian teori, pendapat ahli, dan pendapat pengguna dengan kualifikasi baik; dan (2) mendeskripsikan kualitas produk assessment pembelajaran pada pokok bahasan geometri dan pengukuran yang berorientasi pada aspek pengetahuan, keterampilan dan sikap peserta didik SMP/MTs kelas VII dan VIII berdasarkan aspek kevalidan, kepratisan dan keefektifan. Teknik analisis data yang digunakan untuk menghitung reliabilitas dengan menggunakan α-reliability, untuk α ≥ 60 maka reliabel. Percentage of Agrements (PA) untuk mengetahui tingkat kesepakatan antar pengamat, dengan PA ≥ 70 maka tepenuhi. Hasil penelitian ini menunjukkan bahwa: (1) produk pengembangan perangkat assessment pembelajaran pokok bahasan geometri dan pengukuran yang berorientasi pada aspek pengetahuan, keterampilan dan sikap peserta didik SMP/MTs kelas VII dan VIII sebagai hasil pengembangan berdasarkan kajian teori, pendapat ahli, dan pendapat pengguna mencapai tarap kualifikasi baik. (2) kualitas produk assessment pembelajaran pada pokok bahasan geometri dan pengukuran yang berorientasi pada aspek pengetahuan, keterampilan dan sikap peserta didik SMP/MTs kelas VII dan VIII berdasarkan aspek kevalidan, kepratisan dan keefektifan telah terpenuhi dengan kualitas baik. Kata kunci: assessment, perangkat, matematika. DEVELOPING MATHEMATIC ASSESSMENT PRODUCT OF LEARNING GEOMETRIC AND MEASURING FOR STUDENTS JUNIOR HIGH SCHOOL Abstract The objectives of this research were: (1) to develop mathematic assessment product of learning tools for geometric and measuring subject that was oriented to knowledge, skill, and attitude aspect for students of junior high school grade 7 and 8 according to literature, expert judgement, and user’s opinion that has good qualification; (2) to know the quality of assessment product of geometric and measuring learning tools that was oriented to knowledge, skill, and attitude aspect of students in Junior High School grade 7 and 8 according to validity, effiiciency, and effectiveness aspect. The data were analyzed using α-reliability and precentage of aggrement (PA). It’s realiable for α ≥ 60, while the precentage of aggrement was to know the agreement between observer, it’s fulfilled if PA ≥ 70. The results of this research show that: (1) the development product assessment of learning tools for geometric and mesuring subject that is oriented to knowledge, skill, and attitude aspect for students of junior high school grade 7 and 8 according to literature, expert judgement, and user’s opinion has good qualification; (2) the quality of assessment product of geometric and measuring learning tools that is oriented to knowledge, skill, and attitude aspect of students in Junior High School grade 7 and 8 according to validity, efficiency, and effectiveness aspect is fulfilled well. Keyword: assessment, tools, math.

Стилі APA, Harvard, Vancouver, ISO та ін.

26

Dong, Jiahua, Yang Cong, Gan Sun, Bingtao Ma, and Lichen Wang. "I3DOL: Incremental 3D Object Learning without Catastrophic Forgetting." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 7 (May 18, 2021): 6066–74. http://dx.doi.org/10.1609/aaai.v35i7.16756.

Повний текст джерела

Анотація:

3D object classification has attracted appealing attentions in academic researches and industrial applications. However, most existing methods need to access the training data of past 3D object classes when facing the common real-world scenario: new classes of 3D objects arrive in a sequence. Moreover, the performance of advanced approaches degrades dramatically for past learned classes (i.e., catastrophic forgetting), due to the irregular and redundant geometric structures of 3D point cloud data. To address these challenges, we propose a new Incremental 3D Object Learning (i.e., I3DOL) model, which is the first exploration to learn new classes of 3D object continually. Specifically, an adaptive-geometric centroid module is designed to construct discriminative local geometric structures, which can better characterize the irregular point cloud representation for 3D object. Afterwards, to prevent the catastrophic forgetting brought by redundant geometric information, a geometric-aware attention mechanism is developed to quantify the contributions of local geometric structures, and explore unique 3D geometric characteristics with high contributions for classes incremental learning. Meanwhile, a score fairness compensation strategy is proposed to further alleviate the catastrophic forgetting caused by unbalanced data between past and new classes of 3D object, by compensating biased prediction for new classes in the validation phase. Experiments on 3D representative datasets validate the superiority of our I3DOL framework.

Стилі APA, Harvard, Vancouver, ISO та ін.

27

Selmer, Sarah J., and Kimberly Floyd. "UDL for Geometric Length Measurement." Teaching Children Mathematics 19, no. 3 (October 2012): 146–51. http://dx.doi.org/10.5951/teacchilmath.19.3.0146.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

28

Cantika Dinda Karisma, Yuniawatika, and Erif Ahdhianto. "Analisis Kebutuhan Media Pembelajaran Matematika Bangun Ruang Pada Siswa Kelas V Sekolah Dasar." Jurnal Pemikiran dan Pengembangan Sekolah Dasar (JP2SD) 11, no. 2 (September 30, 2023): 265–76. http://dx.doi.org/10.22219/jp2sd.v11i2.28175.

Повний текст джерела

Анотація:

In learning mathematics, students need help understanding geometric material. Students' success in learning geometric shapes is still low because the teacher uses teaching that is still conventional and has yet to implement innovative learning media. Important media used to support the learning process. This research aimed to analyze the media needs in learning geometric material in VA class at SDN Sambirejo 1, which followed the students' character and was practically used to provide a meaningful learning experience. This study employed qualitative research methods by analyzing descriptive data from interviews and observations with fifth-grade teachers and distributing student needs packages. The research found that there were still few learning media in schools, teachers used blackboards and books, no exciting media, especially for geometric material that could help students understand abstract material, and most students needed media in learning. Mathematics, especially geometric material, is needed to increase enthusiasm and motivation during learning. It can be interpreted that students and teachers need game-based media or games that are practical to support the mathematics learning process, predominantly geometric material.

Стилі APA, Harvard, Vancouver, ISO та ін.

29

Leng, Zhen, Jing Chen, and Songnan Lin. "Learning Instance Motion Segmentation With Geometric Embedding." IEEE Access 9 (2021): 56812–21. http://dx.doi.org/10.1109/access.2021.3062673.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

30

Jaelani, Anton. "Geometric thinking in learning distance and angle." Journal of Physics: Conference Series 1778, no. 1 (February 1, 2021): 012022. http://dx.doi.org/10.1088/1742-6596/1778/1/012022.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

31

Chien, Eli, Antonia Tulino, and Jaime Llorca. "Active Learning in the Geometric Block Model." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 04 (April 3, 2020): 3641–48. http://dx.doi.org/10.1609/aaai.v34i04.5772.

Повний текст джерела

Анотація:

The geometric block model is a recently proposed generative model for random graphs that is able to capture the inherent geometric properties of many community detection problems, providing more accurate characterizations of practical community structures compared with the popular stochastic block model. Galhotra et al. recently proposed a motif-counting algorithm for unsupervised community detection in the geometric block model that is proved to be near-optimal. They also characterized the regimes of the model parameters for which the proposed algorithm can achieve exact recovery. In this work, we initiate the study of active learning in the geometric block model. That is, we are interested in the problem of exactly recovering the community structure of random graphs following the geometric block model under arbitrary model parameters, by possibly querying the labels of a limited number of chosen nodes. We propose two active learning algorithms that combine the use of motif-counting with two different label query policies. Our main contribution is to show that sampling the labels of a vanishingly small fraction of nodes (sub-linear in the total number of nodes) is sufficient to achieve exact recovery in the regimes under which the state-of-the-art unsupervised method fails. We validate the superior performance of our algorithms via numerical simulations on both real and synthetic datasets.

Стилі APA, Harvard, Vancouver, ISO та ін.

32

Yerushalmy, Michal, and Richard A. Houde. "The Geometric Supposer: Promoting Thinking and Learning." Mathematics Teacher 79, no. 6 (September 1986): 418–22. http://dx.doi.org/10.5951/mt.79.6.0418.

Повний текст джерела

Анотація:

Traditionally, the teaching of high school geometry has emphasized the principles of deductive systems. This approach often forces students to learn how to manipulate mathematical systems while it denies them an equal opportunity to create geometry. Geometry teachers have always faced the dilemma of having to instil in their students an appreciation of deductive mathematical systems while at the same time offering them an opportunity to create mathematics. This article describes our approach in dealing with this dilemma.

Стилі APA, Harvard, Vancouver, ISO та ін.

33

Or, C. C. F., and H. R. Wilson. "Implicit face prototype learning from geometric information." Journal of Vision 11, no. 11 (September 23, 2011): 591. http://dx.doi.org/10.1167/11.11.591.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

34

Bronstein, Michael M., Joan Bruna, Yann LeCun, Arthur Szlam, and Pierre Vandergheynst. "Geometric Deep Learning: Going beyond Euclidean data." IEEE Signal Processing Magazine 34, no. 4 (July 2017): 18–42. http://dx.doi.org/10.1109/msp.2017.2693418.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

35

Liang, Jianqing, Qinghua Hu, Pengfei Zhu, and Wenwu Wang. "Efficient multi-modal geometric mean metric learning." Pattern Recognition 75 (March 2018): 188–98. http://dx.doi.org/10.1016/j.patcog.2017.02.032.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

36

Berkiten, Sema, Maciej Halber, Justin Solomon, Chongyang Ma, Hao Li, and Szymon Rusinkiewicz. "Learning Detail Transfer based on Geometric Features." Computer Graphics Forum 36, no. 2 (May 2017): 361–73. http://dx.doi.org/10.1111/cgf.13132.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

37

Or, Charles C. F., and Hugh R. Wilson. "Implicit face prototype learning from geometric information." Vision Research 82 (April 2013): 1–12. http://dx.doi.org/10.1016/j.visres.2013.02.002.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

38

Perham, Arnold E., C. S. V., Bernadette H. Perham, and Faustine L. Perham. "Creating a Learning Environment for Geometric Reasoning." Mathematics Teacher 90, no. 7 (October 1997): 521–42. http://dx.doi.org/10.5951/mt.90.7.0521.

Повний текст джерела

Анотація:

Geometry teachers can introduce the theorems of Euclidean geometry in various ways. Complementing the standbys of the past, namely, compass-and-straightedge constructions and manipulatives, are geometry-construction software, spreadsheets, and programmable graphing calculators.

Стилі APA, Harvard, Vancouver, ISO та ін.

39

Zhu, Zonghai, Zhe Wang, Dongdong Li, Yujin Zhu, and Wenli Du. "Geometric Structural Ensemble Learning for Imbalanced Problems." IEEE Transactions on Cybernetics 50, no. 4 (April 2020): 1617–29. http://dx.doi.org/10.1109/tcyb.2018.2877663.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

40

IKEDA, K. "Geometric Properties of Quasi-Additive Learning Algorithms." IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences E89-A, no. 10 (October 1, 2006): 2812–17. http://dx.doi.org/10.1093/ietfec/e89-a.10.2812.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

41

Bshouty, Nader H., Sally A. Goldman, and H. David Mathias. "Noise-Tolerant Parallel Learning of Geometric Concepts." Information and Computation 147, no. 1 (November 1998): 89–110. http://dx.doi.org/10.1006/inco.1998.2737.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

42

Pan, Ziqi, Li Niu, and Liqing Zhang. "Geometric Inductive Biases for Identifiable Unsupervised Learning of Disentangled Representations." Proceedings of the AAAI Conference on Artificial Intelligence 37, no. 8 (June 26, 2023): 9372–80. http://dx.doi.org/10.1609/aaai.v37i8.26123.

Повний текст джерела

Анотація:

The model identifiability is a considerable issue in the unsupervised learning of disentangled representations. The PCA inductive biases revealed recently for unsupervised disentangling in VAE-based models are shown to improve local alignment of latent dimensions with principal components of the data. In this paper, in additional to the PCA inductive biases, we propose novel geometric inductive biases from the manifold perspective for unsupervised disentangling, which induce the model to capture the global geometric properties of the data manifold with guaranteed model identifiability. We also propose a Geometric Disentangling Regularized AutoEncoder (GDRAE) that combines the PCA and the proposed geometric inductive biases in one unified framework. The experimental results show the usefulness of the geometric inductive biases in unsupervised disentangling and the effectiveness of our GDRAE in capturing the geometric inductive biases.

Стилі APA, Harvard, Vancouver, ISO та ін.

43

Rodríguez, Claudia Orozco, Erla M. Morales Morgado, and Filomena Gonçalves da Silva Cordeir Moita. "Learning Objects and Geometric Representation for Teaching “Definition and Applications of Geometric Vector”." Journal of Cases on Information Technology 17, no. 1 (January 2015): 13–30. http://dx.doi.org/10.4018/jcit.2015010102.

Повний текст джерела

Анотація:

Often during the teaching of mathematics, students have difficulties to understand some abstract concepts. That's why it is necessary to show the student the concepts as clearly and definitely as possible. The proposal of this project is a teaching strategy. It is the use of Geometric Representation integrated Learning Objects for the internalization of concepts. The research process involves the design, development, and evaluation of Learning Objects and how it promotes understanding of the contents of the topic “Real Geometric Vectors and their application”. At the beginning of this article are the context and the latest research concerning to this project. Then an overview of the theoretical framework that supports this work is shown. Finally, the paper describes the methodology used in the project, results of data, expected contributions and conclusions.

Стилі APA, Harvard, Vancouver, ISO та ін.

44

Ananda, Wella, Mardiah Syofiana, Selvi Riwayati, Risnanosanti Risnanosanti, Rahmat Jumri, Adi Asmara, and Winda Ramadianti. "Utilization of Building Blocks for Fun Elementary Mathematics Learning." JATI EMAS (Jurnal Aplikasi Teknik dan Pengabdian Masyarakat) 7, no. 3 (August 6, 2023): 79. http://dx.doi.org/10.36339/je.v7i3.773.

Повний текст джерела

Анотація:

Utilization of geometric blocks in elementary mathematics learning can increase students' interest and activeness in learning mathematics. This activity aims to explore the use of geometric blocks as a fun learning medium in elementary mathematics learning. The method used is a descriptive approach through observation, interviews, and documentation. The target of the activity is 29 grade 5 students at SD Negeri 38 Bengkulu City. The results of the activity show that the use of geometric blocks in elementary mathematics learning can increase students' interest and activeness in learning. Students are more interested and enthusiastic in participating in learning. The use of geometric blocks can also improve understanding of mathematical concepts. Students can easily visualize and understand geometric concepts such as cubes, beams and prisms. This activity makes an important contribution to the development of innovative and fun elementary mathematics learning. Utilization of building blocks as learning media can be used as an effective alternative to increase students' interest and achievement in mathematics.

Стилі APA, Harvard, Vancouver, ISO та ін.

45

den Borre, I. V. "GEOMETRICS DEEP LEARNING APPLICATIONS IN ORTHOPAEDIC RESEARCH." Orthopaedic Proceedings 106-B, SUPP_1 (January 2, 2024): 52. http://dx.doi.org/10.1302/1358-992x.2024.1.052.

Повний текст джерела

Анотація:

Geometric deep learning is a relatively new field that combines the principles of deep learning with techniques from geometry and topology to analyze data with complex structures, such as graphs and manifolds. In orthopedic research, geometric deep learning has been applied to a variety of tasks, including the analysis of imaging data to detect and classify abnormalities, the prediction of patient outcomes following surgical interventions, and the identification of risk factors for degenerative joint disease. This review aims to summarize the current state of the field and highlight the key findings and applications of geometric deep learning in orthopedic research. The review also discusses the potential benefits and limitations of these approaches and identifies areas for future research. Overall, the use of geometric deep learning in orthopedic research has the potential to greatly advance our understanding of the musculoskeletal system and improve patient care.

Стилі APA, Harvard, Vancouver, ISO та ін.

46

ANAMOVA, Rushana R., and Lidiya G. NARTOVA. "GEOMETRIC SPATIAL ABILITY AS AN ELEMENT OF COGNITIVE LEARNING PROCESS." Periódico Tchê Química 16, no. 32 (August 20, 2019): 542–50. http://dx.doi.org/10.52571/ptq.v16.n32.2019.560_periodico32_pgs_542_550.pdf.

Повний текст джерела

Анотація:

University professors more and more often face serious problems of learning geometry and graphic disciplines. In this regard, it is very relevant to obtain a maximum efficient method to teach geometry and graphic disciplines. The purpose of the study is to test the hypothesis that the cause of problems arising in the process of mastering the geometric and graphic disciplines is the violation of continuity of the educational material and the low level of spatial ability of students. In the research, interviewing method (testing) and statistic method have been applied to process the results. It is established that spatial imagination helps a person to perceive the shape of geometric objects by involving him/her into the cognitive process of feeling and control of spatial objects. Students who learned in school technical drawing the same as students who did not learn experience difficulties in mastering the geometric and graphic disciplines. For students who learned technical drawing in schools, the cause of bad retention of the material of the geometric and graphic discipline is low geometric spatial ability. For students who did not learn technical drawing in school, but who demonstrated a high geometric spatial ability, the cause of difficulties in the retention of the geometric and graphic disciplines are connected with the violation of continuity of the educational material. To effectively teach the geometric and graphic disciplines, it is necessary to apply methods of developments of the geometric spatial ability and to form the content of discipline using the principle of continuity.

Стилі APA, Harvard, Vancouver, ISO та ін.

47

Ratnadewi, Ratnadewi, Agus Prijono, and Ariesa Pandanwangi. "Geometry Learning Through Batik Reconstruction." JTAM (Jurnal Teori dan Aplikasi Matematika) 6, no. 4 (October 7, 2022): 1004. http://dx.doi.org/10.31764/jtam.v6i4.9964.

Повний текст джерела

Анотація:

In this world, the shapes of objects, including Batik motifs in Indonesia, are regular and irregular. One of the regular Batik motifs is Surya Kawung Batik from Mojokerto. The purpose of this research is to observe the ability of the Electrical Engineering Department students in Maranatha Christian University to study and reconstruct the geometric shapes of Surya Kawung Batik. In the making of the Batik motifs, the research methods employed are survey, observation, exploration, testing, and improvement, while in the learning process, the method applied is descriptive qualitative, in which the researchers check the data credibility. Turtle graphics algorithm and mathematical calculations are used to form Batik geometric motifs. The result of this research shows an increase in the students' ability to learn the geometric shapes and to reconstruct digital Batik motifs which resemble the original Batik motifs and which can be stored using a smaller memory. If the memory for storing motifs is small, the required storage space will be more efficient.

Стилі APA, Harvard, Vancouver, ISO та ін.

48

Lumbanbatu, Grace Theo Fanny, Atikah Dapriani Lubis, Sontioka Iyolanda Margaretha Lumban Tobing, Putri Sadaria Simangunsong, and Laurensia M. Perangin Angin. "Analysis of the Application of Bruner's Theory in Improving Mathematics Learning Outcomes in Geometry Materials at SD Negeri 14 Sei Meranti." Journal of Educational Analytics 2, no. 2 (June 5, 2023): 295–306. http://dx.doi.org/10.55927/jeda.v2i2.4422.

Повний текст джерела

Анотація:

Bruner's learning theory is a student-centered discovery learning model. This study aims to determine the application of Bruner's theory in improving student mathematics learning outcomes. This study used qualitative research methods. Students learn through active engagement with concepts and principles, and teachers encourage students to gain experience by engaging in activities that allow them to discover concepts and principles for themselves. In using Brunner's theory in geometric learning it can be said to be successful because it helps students to understand and recognize the parts of geometric shapes and geometric materials. Based on these results, it means that the application of Bruner's theory can improve student learning outcomes in elementary school geometric learning.

Стилі APA, Harvard, Vancouver, ISO та ін.

49

Nan, Xiaohu, and Lei Ding. "Learning Geometric Feature Embedding with Transformers for Image Matching." Sensors 22, no. 24 (December 15, 2022): 9882. http://dx.doi.org/10.3390/s22249882.

Повний текст джерела

Анотація:

Local feature matching is a part of many large vision tasks. Local feature matching usually consists of three parts: feature detection, description, and matching. The matching task usually serves a downstream task, such as camera pose estimation, so geometric information is crucial for the matching task. We propose the geometric feature embedding matching method (GFM) for local feature matching. We propose the adaptive keypoint geometric embedding module dynamic adjust keypoint position information and the orientation geometric embedding displayed modeling of geometric information about rotation. Subsequently, we interleave the use of self-attention and cross-attention for local feature enhancement. The predicted correspondences are multiplied by the local features. The correspondences are solved by computing dual-softmax. An intuitive human extraction and matching scheme is implemented. In order to verify the effectiveness of our proposed method, we performed validation on three datasets (MegaDepth, Hpatches, Aachen Day-Night v1.1) according to their respective metrics, and the results showed that our method achieved satisfactory results in all scenes.

Стилі APA, Harvard, Vancouver, ISO та ін.

50

Clements, Douglas H., and Michael T. Battista. "Computer Environments for Learning Geometry." Journal of Educational Computing Research 10, no. 2 (March 1994): 173–97. http://dx.doi.org/10.2190/8074-298a-ktl2-uqvw.

Повний текст джерела

Анотація:

Given their graphic capabilities, computers may facilitate the construction of geometric concepts. Comparative media research, however, reveals few differences between media; alterations in curricula or teaching strategies might also explain the positive results of many studies that compare computer to noncomputer media. Yet, there remain certain computer functions that non-computer media may not easily duplicate. This article reviews research to describe such functions of construction-oriented environments and to evaluate their unique contributions to students' learning of geometry. Implications for the design of geometric computer environments for geometry education are drawn.

Стилі APA, Harvard, Vancouver, ISO та ін.

Статті в журналах з теми "Geometric learning"

Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями