Algorithms to estimate Shapley value feature attributions

H Chen, IC Covert, SM Lundberg, SI Lee - Nature Machine Intelligence, 2023 - nature.com
Feature attributions based on the Shapley value are popular for explaining machine
learning models. However, their estimation is complex from both theoretical and …

Machine-learned potentials for next-generation matter simulations

P Friederich, F Häse, J Proppe, A Aspuru-Guzik - Nature Materials, 2021 - nature.com
The choice of simulation methods in computational materials science is driven by a
fundamental trade-off: bridging large time-and length-scales with highly accurate …

Compute trends across three eras of machine learning

J Sevilla, L Heim, A Ho, T Besiroglu… - … Joint Conference on …, 2022 - ieeexplore.ieee.org
Compute, data, and algorithmic advances are the three fundamental factors that drive
progress in modern Machine Learning (ML). In this paper we study trends in the most readily …

Structural crack detection using deep convolutional neural networks

R Ali, JH Chuah, MSA Talip, N Mokhtar… - Automation in …, 2022 - Elsevier
Abstract Convolutional Neural Networks (CNN) have immense potential to solve a broad
range of computer vision problems. It has achieved encouraging results in numerous …

[ΒΙΒΛΙΟ][B] Deep learning

JD Kelleher - 2019 - books.google.com
An accessible introduction to the artificial intelligence technology that enables computer
vision, speech recognition, machine translation, and driverless cars. Deep learning is an …

Deep convolutional neural networks for image classification: A comprehensive review

W Rawat, Z Wang - Neural computation, 2017 - ieeexplore.ieee.org
Convolutional neural networks (CNNs) have been applied to visual tasks since the late
1980s. However, despite a few scattered applications, they were dormant until the mid …

Deep learning‐based crack damage detection using convolutional neural networks

YJ Cha, W Choi, O Büyüköztürk - Computer‐Aided Civil and …, 2017 - Wiley Online Library
A number of image processing techniques (IPTs) have been implemented for detecting civil
infrastructure defects to partially replace human‐conducted onsite inspections. These IPTs …

SDDNet: Real-time crack segmentation

W Choi, YJ Cha - IEEE Transactions on Industrial Electronics, 2019 - ieeexplore.ieee.org
This article reports the development of a pure deep learning method for segmenting
concrete cracks in images. The objectives are to achieve the real-time performance while …

[ΒΙΒΛΙΟ][B] Deep learning

I Goodfellow - 2016 - books.google.com
An introduction to a broad range of topics in deep learning, covering mathematical and
conceptual background, deep learning techniques used in industry, and research …