Results 31 to 40 of about 293,454 (315)

A fast compression-based similarity measure with applications to content-based image retrieval [PDF]

, 2011
Compression-based similarity measures are effectively employed in applications on diverse data types with a basically parameter-free approach. Nevertheless, there are problems in applying these techniques to medium-to-large datasets which have been ...
Mihai Datcu, Daniele Cerra, Cerra, Daniele, Datcu, Mihai   +3 more
core   +1 more source

Optimization Based Layer-Wise Pruning Threshold Method for Accelerating Convolutional Neural Networks

Mathematics, 2023
Among various network compression methods, network pruning has developed rapidly due to its superior compression performance. However, the trivial pruning threshold limits the compression performance of pruning.
Yunlong Ding, Di-Rong Chen
doaj   +1 more source

Heuristic Compression Method for CNN Model Applying Quantization to a Combination of Structured and Unstructured Pruning Techniques

IEEE Access
Model Compression is an actively pursued research field in recent years with the goal of deploying state-of-the-art deep neural networks. It is targeted to implementations which are based on power constrained and resource limited devices as the reduced ...
Danhe Tian, Shinichi Yamagiwa, Koichi Wada   +2 more
doaj   +1 more source

Gradual Channel Pruning While Training Using Feature Relevance Scores for Convolutional Neural Networks

IEEE Access, 2020
The enormous inference cost of deep neural networks can be mitigated by network compression. Pruning connections is one of the predominant approaches used for network compression.
Sai Aparna Aketi, Sourjya Roy, Anand Raghunathan, Kaushik Roy   +3 more
doaj   +1 more source

A Modeling of Compressible Droplets in a Fluid [PDF]

Communications in Mathematical Sciences, 2003
zbMATH Open Web Interface contents unavailable due to conflicting licenses.
Boudin, Laurent, Desvillettes, Laurent, Motte, Renaud   +2 more
openaire   +3 more sources

Differentially Private Model Compression

Advances in Neural Information Processing Systems 35, 2022
Recent papers have shown that large pre-trained language models (LLMs) such as BERT, GPT-2 can be fine-tuned on private data to achieve performance comparable to non-private models for many downstream Natural Language Processing (NLP) tasks while simultaneously guaranteeing differential privacy.
Fatemehsadat Mireshghallah, Arturs Backurs, Huseyin A. Inan, Lukas Wutschitz, Janardhan Kulkarni   +4 more
openaire   +3 more sources

Compressed Nonparametric Language Modelling [PDF]

Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, 2017
Hierarchical Pitman-Yor Process priors are compelling for learning language models, outperforming point-estimate based methods. However, these models remain unpopular due to computational and statistical inference issues, such as memory and time usage, as well as poor mixing of sampler.
Ehsan Shareghi, Gholamreza Haffari, Trevor Cohn   +2 more
openaire   +1 more source

An improved ShuffleNetV2 method based on ensemble self-distillation for tomato leaf diseases recognition

Frontiers in Plant Science
IntroductionTimely and accurate recognition of tomato diseases is crucial for improving tomato yield. While large deep learning models can achieve high-precision disease recognition, these models often have a large number of parameters, making them ...
Shuiping Ni, Yue Jia, Mingfu Zhu, Mingfu Zhu, Yizhe Zhang, Wendi Wang, Shangxin Liu, Yawei Chen   +7 more
doaj   +1 more source

Compressed Context Modeling for Text Compression

2011 Data Compression Conference, 2011
In text compression, statistical context modeling aims to construct a model to calculate the probability distribution of a character based upon its context. The order -- $k$ context of a symbol is defined as the string formed by its preceding $k$ symbols.
openaire   +2 more sources

Small pre-trained model for background understanding in multi-round question answering

Frontiers in Artificial Intelligence
Multi-round Q&A based on background text needs to infer the answer to the question through the current question, historical Q&A pairs, and background text.
Xin Huang, Hulin Song, Mingming Lu
doaj   +1 more source