A lightweight residual network based on improved knowledge transfer and quantized distillation for cross-domain fault diagnosis of rolling bearings
W Guo, X Li, Z Shen - Expert Systems with Applications, 2024 - Elsevier
Predictive maintenance advocates the use of artificial intelligence to analyze big data and
provides support for monitoring health conditions and planning maintenance activities in …
provides support for monitoring health conditions and planning maintenance activities in …
Towards Cross-Tokenizer Distillation: the Universal Logit Distillation Loss for LLMs
Deploying large language models (LLMs) of several billion parameters can be impractical in
most industrial use cases due to constraints such as cost, latency limitations, and hardware …
most industrial use cases due to constraints such as cost, latency limitations, and hardware …
Knowledge distillation with insufficient training data for regression
M Kang, S Kang - Engineering Applications of Artificial Intelligence, 2024 - Elsevier
Abstract Knowledge distillation has been widely used to compress a large teacher network
into a smaller student network. Conventional approaches require the training dataset that …
into a smaller student network. Conventional approaches require the training dataset that …
[HTML][HTML] Knowledge Distillation in Image Classification: The Impact of Datasets
AG Belinga, CS Tekouabou Koumetio, M El Haziti… - Computers, 2024 - mdpi.com
As the demand for efficient and lightweight models in image classification grows, knowledge
distillation has emerged as a promising technique to transfer expertise from complex teacher …
distillation has emerged as a promising technique to transfer expertise from complex teacher …
A data-driven target-oriented robust optimization framework: bridging machine learning and optimization under uncertainty
JL San Juan, C Sy - Journal of Industrial and Production …, 2024 - Taylor & Francis
The target-oriented robust optimization (TORO) approach converts the original objectives to
system targets and instead maximizes an uncertainty budget or robustness index. Machine …
system targets and instead maximizes an uncertainty budget or robustness index. Machine …
Task‐oriented feature hallucination for few‐shot image classification
S Wu, X Gao, X Hu - IET Image Processing, 2023 - Wiley Online Library
Data hallucination generates additional training examples for novel classes to alleviate the
data scarcity problem in few‐shot learning (FSL). Existing hallucination‐based FSL methods …
data scarcity problem in few‐shot learning (FSL). Existing hallucination‐based FSL methods …
[PDF][PDF] Towards Cross-Tokenizer Distillation: the Universal Logit Distillation Loss for LLMs
Deploying large language models (LLMs) of several billion parameters can be impractical in
most industrial use cases due to constraints such as cost, latency limitations, and hardware …
most industrial use cases due to constraints such as cost, latency limitations, and hardware …