Neural networkInterpretabilityGradientTo enhance the energy efficiency of heating, ventilation and air conditioning (HVAC) systems, which is a non-linear and complicated system, machine learning has been used intensively. However, traditional white-box machine-learning models with good interpretability ...
A Survey on Neural Network Interpretabilityarxiv.org/abs/2012.14261 摘要: 随着深度神经网络的巨大成功,人们也越来越关注它们的黑匣子特性。可解释性问题影响了人们对深度学习系统的信任。它也与许多伦理问题有关,例如算法歧视。此外,可解释性是深度网络在其他研究领域(如药物发现和基因组学)成为强大工具的一个理...
为了探究网络的可解释性（Interpretability）的是否是与units的排列分布有关，作者对于某一层的所有unit进行...
We propose a neural network (NN) architecture, the Element Spatial Convolution Neural Network (ESCNN), towards the airfoil lift coefficient prediction task. The ESCNN outperforms existing state-of-the-art NNs in terms of prediction accuracy, with two orders of less parameters. We further investig...
which features full interpretability, high accuracy, high generalizability and low model complexity, as superposable neural network (SNN) optimization. We validate our approach by training models on landslide inventories from three different easternmost Himalaya regions. Our SNN outperformed physically-based...
Interpretability research of deep learning: A literature survey 2025, Information Fusion Show abstract Optimized interpretable generalized additive neural network-based human brain diagnosis using medical imaging 2025, Knowledge-Based Systems Show abstract Explainable AI for enhanced decision-making 2024, Decisi...
Interpretability.It might become difficult to understand how a CNN arrives at a specific prediction or output. Overfitting.Without a dropout layer, a CNN might become prone to overfitting. Applications of convolutional neural networks Because processing and interpreting visual data are such common tasks...
. If you are trying to explain an underlying process that produces the relationships between the target and predictors, it would be better to use a more traditional statistical model. However, if model interpretability is not important, you can obtain good predictions using a neural network....
The neural network has made outstanding achievements in many fields, while comparing with traditional machine learning models, the neural network has poor interpretability, which brings great limitation to its practical application. Therefore, many researchers try to combine neural networks with traditional...
Having established that the PNNs learn the physics of the system and result in stable and accurate integrators, we now explore their interpretability in the hope of finding out how time-reversibility and energy conservation are achieved. In short: can the PNNs teach us what they learned? We ...