1,731,153 research outputs found
Dasaset supporting the publication "Late Breaking Results: Adaptive Ensembles of Dynamic DNNs for Collaborative Edge Inference"
No full textThis dataset supports the publication: "Late Breaking Results: Adaptive Ensembles of Dynamic DNNs for Collaborative Edge Inference" by Mingyu Hu, Amit Kumar Singh, Jonathon Hare, Geoff V. Merrett.
CONFERENCE: Design, Automation and Test in Europe Conference 2026
This dataset includes the experimental results for:
Figure 3: Results of Ensemble accuracy from different combinations of 4 model instance of Dynamic ResNet-18.
Figure 4: Comparison of inference latency with different methods under different deadlines.
Figure 5: Comparison of inference accuracy with different methods under different deadlines.</span
Dataset supporting the conference paper "Fluid dynamic DNNs for reliable and adaptive distributed inference on edge devices"
No full textThis dataset supports the publication:
"Fluid Dynamic DNNs for Reliable and Adaptive Distributed Inference on Edge Devices" by Lei Xun, Mingyu Hu, Hengrui Zhao, Amit Kumar Singh, Jonathon Hare, Geoff V. Merrett
CONFERENCE: Design, Automation and Test in Europe Conference 2024
This dataset includes the experimental results for Figure 2 of the paper, showing the throughput and accuracy of the different models (static, dynamic and fluid) considered under different distributed-system cases (master & worker, master, worker).
This dataset contains:
-'data.csv': Data supporting Fig. 2. The throughput and accuracy of the different models (static, dynamic and fluid) considered under different distributed-system cases (master & worker, master, worker).
Related projects: International Centre for Spatial Computational Learning
</span
KumarSupplementalMaterial_rev – Supplemental material for Undervaluing Gratitude: Expressers Misunderstand the Consequences of Showing Appreciation
No full textSupplemental material, KumarSupplementalMaterial_rev for Undervaluing Gratitude: Expressers Misunderstand the Consequences of Showing Appreciation by Amit Kumar and Nicholas Epley in Psychological Science</p
KumarOpenPracticesDisclosure_rev – Supplemental material for Undervaluing Gratitude: Expressers Misunderstand the Consequences of Showing Appreciation
No full textSupplemental material, KumarOpenPracticesDisclosure_rev for Undervaluing Gratitude: Expressers Misunderstand the Consequences of Showing Appreciation by Amit Kumar and Nicholas Epley in Psychological Science</p
A comparative study of stress intensity factor extraction techniques for the generalized finite element method
Full text linkGeneralized Finite Element Method (GFEM) is a Partition of Unity Method where
shape functions are constructed by the product of standard finite element shape
function and some additional shape functions. These additional shape functions
take the benefit of some prior knowledge of the solution. They are especially useful
in fracture mechanics problems where crack singularities are addressed. A
crack can be represented with the help of discontinuous and singular shape functions.
This gives a great flexibility to the user in a choice of an appropriate mesh.
Stress intensity factor is an important quantity in fracture mechanics which is used
to predict the stress state around a crack front. This report presents a comprehensive
study of stress intensity factor extraction techniques: The Contour Integral
Method (CIM), the Cut-off Function Method (CFM) and the Displacement Correlation
Method (DCM). A few techniques are also shown to improve Displacement
Correlation Method with the use of additional sampling points.Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2018-05-01The student, Amit Kumar Dhankhar, accepted the attached license on 2016-04-26 at 22:10.The student, Amit Kumar Dhankhar, submitted this Thesis for approval on 2016-04-26 at 22:20.This Thesis was approved for publication on 2016-04-28 at 09:07.DSpace SAF Submission Ingestion Package generated from Vireo submission #9536 on 2016-07-07 at 14:18:07Made available in DSpace on 2016-07-07T21:18:08Z (GMT). No. of bitstreams: 2
DHANKHAR-THESIS-2016.pdf: 7148295 bytes, checksum: a0e016df9ef345d5a4322910df32a270 (MD5)
LICENSE.txt: 4216 bytes, checksum: b50dd402df436de69f00f40f547f7c07 (MD5)
Previous issue date: 2016-04-28Embargo set by: Seth Robbins for item 93323
Lift date: 2018-07-07T21:18:16Z
Reason: Author requested closed access (OA after 2yrs) in Vireo ETD systemLimited Restriction Lifted for Item 93323 on 2018-07-08T09:15:29Z
Lightweight adaptation of neural language models via subspace embedding
No full textTraditional neural word embeddings are usually dependent on a richer diversity of vocabulary. However, the language models recline to cover major vocabularies via the word embedding parameters, in particular, for multilingual language models that generally cover a significant part of their overall learning parameters. In this work, we present a new compact embedding structure to reduce the memory footprint of the pre-trained language models with a sacrifice of up to 4% absolute accuracy. The embeddings vectors reconstruction follows a set of subspace embeddings and an assignment procedure via the contextual relationship among tokens from pre-trained language models. The subspace embedding structure1calibrates to masked language models, to evaluate our compact embedding structure on similarity and textual entailment tasks, sentence and paraphrase tasks. Our experimental evaluation shows that the subspace embeddings achieve compression rates beyond99.8% in comparison with the original embeddings for the language models on XNLI and GLUE benchmark suites
sj-docx-2-pie-10.1177_09544089221087821 - Supplemental material for Design and development of a rapid prototyping system combining traditional fused deposition modeling and reconfigurable pins platform
No full textSupplemental material, sj-docx-2-pie-10.1177_09544089221087821 for Design and development of a rapid prototyping system combining traditional fused deposition modeling and reconfigurable pins platform by Vikrant Charak and Amit Kumar Sinha in Proceedings of the Institution of Mechanical Engineers, Part E: Journal of Process Mechanical Engineering</p
sj-docx-3-pie-10.1177_09544089221087821 - Supplemental material for Design and development of a rapid prototyping system combining traditional fused deposition modeling and reconfigurable pins platform
No full textSupplemental material, sj-docx-3-pie-10.1177_09544089221087821 for Design and development of a rapid prototyping system combining traditional fused deposition modeling and reconfigurable pins platform by Vikrant Charak and Amit Kumar Sinha in Proceedings of the Institution of Mechanical Engineers, Part E: Journal of Process Mechanical Engineering</p
sj-docx-4-pie-10.1177_09544089221087821 - Supplemental material for Design and development of a rapid prototyping system combining traditional fused deposition modeling and reconfigurable pins platform
No full textSupplemental material, sj-docx-4-pie-10.1177_09544089221087821 for Design and development of a rapid prototyping system combining traditional fused deposition modeling and reconfigurable pins platform by Vikrant Charak and Amit Kumar Sinha in Proceedings of the Institution of Mechanical Engineers, Part E: Journal of Process Mechanical Engineering</p
- …
