Ai alignment: A comprehensive survey

J Ji, T Qiu, B Chen, B Zhang, H Lou, K Wang… - arxiv preprint arxiv …, 2023 - arxiv.org
AI alignment aims to make AI systems behave in line with human intentions and values. As
AI systems grow more capable, the potential large-scale risks associated with misaligned AI …

Machine Learning, Deep Learning and Statistical Analysis for forecasting building energy consumption—A systematic review

M Khalil, AS McGough, Z Pourmirza… - … Applications of Artificial …, 2022 - Elsevier
The building sector accounts for 36% of the total global energy usage and 40% of
associated Carbon Dioxide emissions. Therefore, the forecasting of building energy …

A simple and effective pruning approach for large language models

M Sun, Z Liu, A Bair, JZ Kolter - arxiv preprint arxiv:2306.11695, 2023 - arxiv.org
As their size increases, Large Languages Models (LLMs) are natural candidates for network
pruning methods: approaches that drop a subset of network weights while striving to …

b-darts: Beta-decay regularization for differentiable architecture search

P Ye, B Li, Y Li, T Chen, J Fan… - proceedings of the …, 2022 - openaccess.thecvf.com
Abstract Neural Architecture Search (NAS) has attracted increasingly more attention in
recent years because of its capability to design deep neural network automatically. Among …

Covid-transformer: Interpretable covid-19 detection using vision transformer for healthcare

D Shome, T Kar, SN Mohanty, P Tiwari… - International Journal of …, 2021 - mdpi.com
In the recent pandemic, accurate and rapid testing of patients remained a critical task in the
diagnosis and control of COVID-19 disease spread in the healthcare industry. Because of …

Large separable kernel attention: Rethinking the large kernel attention design in cnn

KW Lau, LM Po, YAU Rehman - Expert Systems with Applications, 2024 - Elsevier
Abstract Visual Attention Networks (VAN) with Large Kernel Attention (LKA) modules have
been shown to provide remarkable performance, that surpasses Vision Transformers (ViTs) …

DNoiseNet: Deep learning-based feedback active noise control in various noisy environments

YJ Cha, A Mostafavi, SS Benipal - Engineering Applications of Artificial …, 2023 - Elsevier
The use of active noise control/cancelation (ANC) has increased because of the availability
of efficient circuits and computational power. However, most ANC systems are based on …

Automatic concrete crack segmentation model based on transformer

W Wang, C Su - Automation in Construction, 2022 - Elsevier
Routine visual inspection of concrete structures is essential to maintain safe conditions.
Therefore, studies of concrete crack segmentation using deep learning methods have been …

Learning from teaching regularization: Generalizable correlations should be easy to imitate

C **, T Che, H Peng, Y Li, DN Metaxas… - arxiv preprint arxiv …, 2024 - arxiv.org
Generalization remains a central challenge in machine learning. In this work, we propose
Learning from Teaching (LoT), a novel regularization technique for deep neural networks to …

Coaid-deep: An optimized intelligent framework for automated detecting covid-19 misleading information on twitter

DS Abdelminaam, FH Ismail, M Taha, A Taha… - Ieee …, 2021 - ieeexplore.ieee.org
COVID-19 has affected all peoples' lives. Though COVID-19 is on the rising, the existence of
misinformation about the virus also grows in parallel. Additionally, the spread of …