AIMC Topic: Models, Theoretical

Clear Filters Showing 31 to 40 of 1827 articles

Derivational morphology reveals analogical generalization in large language models.

Proceedings of the National Academy of Sciences of the United States of America
What mechanisms underlie linguistic generalization in large language models (LLMs)? This question has attracted considerable attention, with most studies analyzing the extent to which the language skills of LLMs resemble rules. As of yet, it is not k...

A controller of robot constant force grinding based on proximal policy optimization algorithm.

PloS one
In order to solve the problems of high dependence on the accuracy of environmental model and poor environmental adaptability of traditional control methods, the robot constant force grinding controller that based on proximal policy optimization was p...

A simple yet effective approach for predicting disease spread using mathematically-inspired diffusion-informed neural networks.

Scientific reports
The COVID-19 outbreak has highlighted the importance of mathematical epidemic models like the Susceptible-Infected-Recovered (SIR) model, for understanding disease spread dynamics. However, enhancing their predictive accuracy complicates parameter es...

Using large language models to learn from recent climate change discourse in public health.

PloS one
BACKGROUND: Public health has increasingly recognized the links between climate change and health, emphasizing the need to address related inequities. This is reflected in work led by the Intergovernmental Panel on Climate Change, the UN Framework Co...

Prompt architecture induces methodological artifacts in large language models.

PloS one
We examine how the seemingly arbitrary way a prompt is posed, which we term "prompt architecture," influences responses provided by large language models (LLMs). Five large-scale, full-factorial experiments performing standard (zero-shot) similarity ...

Inversion of lake transparency using remote sensing and deep hybrid recurrent models.

Ecotoxicology and environmental safety
Utilizing computer technology and remote sensing data, the extraction of water-related features of lakes has become a hot topic in lake ecological research. Addressing challenges like the high optical complexity of lake water bodies, the inadequacy o...

Session interest model for CTR prediction based on feature co-action network.

Scientific reports
The main purpose of click-prediction models is to predict the probability of customers clicking on products and provide support for advertising decisions of businesses. However, most previous models often use deep neural networks to capture implicit ...

Some novel concepts of interval-valued q-rung orthopair fuzzy graphs and computational framework of fuzzy air conditioning system.

PloS one
The interval-valued q-rung orthopair fuzzy sets being an extension of interval-valued intuitionistic and interval-valued Pythagorean fuzzy sets is more flexible model to address vague information that has only two attributes yes or no. The combinatio...

An interpretable approach to estimate the self-motion in fish-like robots using mode decomposition analysis.

Nature communications
The artificial lateral line system, composed of velocity and pressure sensors, is the sensing system for fish-like robots by mimicking the lateral line system of aquatic organisms. However, accurately estimating the self-motion of the fish-like robot...

Adaptive lift chiller units fault diagnosis model based on machine learning.

PloS one
The early minor faults generated by the chiller in operation are not easy to perceive, and the severity will gradually increase with time. The traditional fault diagnosis method has low accuracy and poor stability for early fault diagnosis. In this p...