Deep learning is becoming increasingly adopted in business and industry due to its ability to transform large quantities of data into high-performing models. These models, however, are generally regarded as black boxes, which, in spite of their performance, could prevent their use. In this context, the field of eXplainable AI attempts to develop techniques that temper the impenetrable nature of the models and promote a level of understanding of their behavior. Here we present our contribution to XAI methods in the form of a framework that we term SpecXAI, which is based on the spectral characterization of the entire network. We show how this framework can be used to not only understand the network but also manipulate it into a linear interpretable symbolic representation.
Balancing Interpretability and Performance in Reinforcement Learning: An Adaptive Spectral Based Linear Approach
Center for Intelligent Decision Making and Machine Learning, School of Management, Xi’an Jiaotong University, Xi’an, China(智能决策与机器学习中心,管理学院,西安交通大学);Department of Mathematics, Hong Kong Baptist University, Kowloon, Hong Kong(数学系,香港 Baptist 大学)
A Biologically Interpretable Two-stage Deep Neural Network (BIT-DNN) For Vegetation Recognition From Hyperspectral Imagery
Manchester Metropolitan University(曼彻斯特城市大学);Aerospace Information Research Institute, Chinese Academy of Sciences(中国科学院空天信息创新研究院);Brunel University(布鲁内尔大学)
Generalization Analysis and Method for Domain Generalization for a Family of Recurrent Neural Networks
Department of Electrical and Computer Engineering at the University of Manitoba(曼尼托巴大学电气与计算机工程系);Department of Computer Science, Toronto Metropolitan University(多伦多 Metropolitan 大学计算机科学系)
Noise Conscious Training of Non Local Neural Network powered by Self Attentive Spectral Normalized Markovian Patch GAN for Low Dose CT Denoising
在医疗实践中使用计算机断层扫描(CT)成像的爆炸性增长,提高了公众对患者相关辐射剂量的关注。然而,减少辐射剂量导致噪声和伪影增加,这不利地降低了扫描的可解释性。因此,一种先进的图像重建算法来提高低剂量ct的诊断性能成为研究人员的主要关注点,但由于该问题的不适定性,这具有挑战性。近年来,基于深度学习的技术已经成为低剂量CT(LDCT)去噪的主要方法。然而,仍然存在一些常见的瓶颈,这阻碍了基于深度学习的技术提供最佳性能。在这项研究中,我们试图减轻这些问题与三个新的吸积。首先,我们提出了一种新的卷积模块作为第一次尝试利用CT图像的邻域相似性去噪任务。我们提出的模块有助于提高去噪的显著幅度。接下来,我们转向CT噪声的非平稳性问题,并引入了一种新的噪声感知均方误差损失用于LDCT去噪。此外,上述损失也有助于减轻使用图像补丁训练CT去噪网络时所需的繁重工作。最后,我们提出了一种新的CT去噪任务的函数。传统的香草型协议往往忽略了精细的结构细节,而专注于全球协议。我们提出的神经网络利用自注意力和像素级GANs来恢复LDCT图像的诊断质量。我们的方法在2016年NIH-AAPM-Mayo Clinic低剂量CT Grand Challenge的公开数据集上进行了验证,其表现明显优于现有的最先进方法。
Interpretable Spectral Variational AutoEncoder (ISVAE) for time series clustering
Universidad Carlos III de Madrid(马德里卡洛斯三世大学);Instituto de Investigación Sanitaria Gregorio Marañón(格雷戈里奥·马拉尼翁卫生研究所);Evidence Based Behaviour (eB2)(循证行为(eB2));Oxford-Man Institute of Quantitative Finance, University of Oxford(牛津大学牛津-曼氏定量金融研究所)
Scientific Machine Learning with Kolmogorov-Arnold Networks
Energy \& Intelligence Lab, Department of Chemical Engineering, University of Utah, Salt Lake City, Utah 84112, USA;Department of Mechanical Engineering, School of Engineering, Urmia University of Technology, Urmia, Iran