involving or characterized by conflict or opposition
Example: For that we propose a novel method for generating one-pixel adversarial perturbations based on differential evolution (DE).
Su, J., Vargas, D. V., & Sakurai, K. (2019). One pixel attack for fooling deep neural networks. IEEE Transactions on Evolutionary Computation, 23(5), 828-841.
ru: состязательный
alignment
noun
arrangement in a straight line or in correct relative positions.
Example: apply cross-lingual alignment of contextual word representation to zero-shot dependency
Ramesh, A., Pavlov, M., Goh, G., Gray, S., Voss, C., Radford, A., ... & Sutskever, I. (2021, July). Zero-shot text-to-image generation. In International Conference on Machine Learning (pp. 8821-8831). PMLR.
ru: выравнивание
convolution
noun
a function derived from two given functions by integration which expresses how the shape of one is modified by the other.
Example: The use of 1x1 convolutions at the end of the encoder and the beginning of the decoder.
Ramesh, A., Pavlov, M., Goh, G., Gray, S., Voss, C., Radford, A., ... & Sutskever, I. (2021, July). Zero-shot text-to-image generation. In International Conference on Machine Learning (pp. 8821-8831). PMLR.
ru: свёртка
geared
adjective
to make, change or prepare something so that it is suitable for a particular purpose
Example: For a discussion specifically geared towards mathematical audience
A. Andoni, P. Indyk, and I. Razenshteyn, ‘Approximate Nearest Neighbor Search in High Dimensions’, arXiv:1806.09823 [cs, stat], Jun. 2018, Accessed: Jan. 07, 2022. [Online]. Available: http://arxiv.org/abs/1806.09823
ru: нацеленный
generic
adjective
characteristic of or relating to a class or group of things; not specific.
Example: By now, many publications (for instance refs. 16–18) characterize approximation properties of generic multilayer networks.
T. Poggio, A. Banburski, and Q. Liao, ‘Theoretical issues in deep networks’, Proc Natl Acad Sci USA, vol. 117, no. 48, pp. 30039–30045, Dec. 2020, doi: 10.1073/pnas.1907369117.
ru: обобщенный
gullible
adjective
easily persuaded to believe something; credulous.
Example: In the end, the gullible will delegate to some automatic text producer the last word, like today they ask existential questions to Google
Floridi, L., & Chiriatti, M. (2020). GPT-3: Its nature, scope, limits, and consequences. Minds and Machines, 30(4), 681-694.
ru: доверчивый
imminent
adjective
about to happen.
Example: We believe that the most imminent implications of our results are theoretical in nature.
M. Hahn, ‘Theoretical Limitations of Self-Attention in Neural Sequence Models’, Transactions of the Association for Computational Linguistics, vol. 8, pp. 156–171, 2020, doi: 10.1162/tacl_a_00306.
ru: неизбежный
induce
verb
to bring about, cause, generate
Example: Retrospectively, the mapping can be viewed as being induced by an adjacency matrix
A. Andoni, P. Indyk, and I. Razenshteyn, ‘Approximate Nearest Neighbor Search in High Dimensions’, arXiv:1806.09823 [cs, stat], Jun. 2018, Accessed: Jan. 07, 2022. [Online]. Available: http://arxiv.org/abs/1806.09823
ru: порождать
pooling
noun
share (resources or information) for the benefit of all involved.
Example: Thanks to the ability to handle image misalignment while keeping important structural information in the pooling stage, it improves the classification accuracy significantly.
Ryu, J., Yang, M. H., & Lim, J. (2018). Dft-based transformation invariant pooling layer for visual classification. In Proceedings of the European Conference on Computer Vision (ECCV) (pp. 84-99).
ru: объединение
rectifier
noun
an electronic device that converts an alternating current into a direct current
Example: and O(N) layers with O(N^2) rectifier linear units in total to construct the polynomial P^N
S. Liang and R. Srikant, ‘Why Deep Neural Networks for Function Approximation?’ arXiv, Mar. 03, 2017. Accessed: Nov. 10, 2022. [Online]. Available: http://arxiv.org/abs/1610.04161