Estimation with Uncertainty via Conditional Generative Adversarial Networks

Conventional predictive Artificial Neural Networks (ANNs) commonly employ deterministic weight matrices; therefore, their prediction is a point estimate. Such a deterministic nature in ANNs causes the limitations of using ANNs for medical diagnosis, law problems, and portfolio management, in which discovering not only the prediction but also the uncertainty of the prediction is essentially required. To address such a problem, we propose a predictive probabilistic neural network model, which corresponds to a different manner of using the generator in conditional Generative Adversarial Network (cGAN) that has been routinely used for conditional sample generation. By reversing the input and output of ordinary cGAN, the model can be successfully used as a predictive model; besides, the model is robust against noises since adversarial training is employed. In addition, to measure the uncertainty of predictions, we introduce the entropy and relative entropy for regression problems and classification problems, respectively. The proposed framework is applied to stock market data and an image classification task. As a result, the proposed framework shows superior estimation performance, especially on noisy data; moreover, it is demonstrated that the proposed framework can properly estimate the uncertainty of predictions.

[1]  Junhee Seok,et al.  Portfolio management via two-stage deep learning with a joint cost , 2020, Expert Syst. Appl..

[2]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Sigifredo Laengle,et al.  Mean-Variance Portfolio Selection With the Ordered Weighted Average , 2017, IEEE Transactions on Fuzzy Systems.

[4]  Aditya M. Sharma,et al.  COVLIAS 1.0: Lung Segmentation in COVID-19 Computed Tomography Scans Using Hybrid Deep Learning Artificial Intelligence Models , 2021, Diagnostics.

[5]  Junhee Seok,et al.  Improved recurrent generative adversarial networks with regularization techniques and a controllable framework , 2020, Inf. Sci..

[6]  Julien Cornebise,et al.  Weight Uncertainty in Neural Network , 2015, ICML.

[7]  Kemeng Bai,et al.  Centered Multi-Task Generative Adversarial Network for Small Object Detection , 2021, Sensors.

[8]  Junhee Seok,et al.  Controllable Generative Adversarial Network , 2017, IEEE Access.

[9]  Zengchang Qin,et al.  Auto-painter: Cartoon image generation from sketch by using conditional Wasserstein generative adversarial networks , 2018, Neurocomputing.

[10]  Alex Kendall,et al.  What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision? , 2017, NIPS.

[11]  Zhe Gan,et al.  AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[12]  Kilian Q. Weinberger,et al.  CondenseNet: An Efficient DenseNet Using Learned Group Convolutions , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[13]  Kaiming He,et al.  Exploring Randomly Wired Neural Networks for Image Recognition , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[14]  Yuichi Yoshida,et al.  Spectral Normalization for Generative Adversarial Networks , 2018, ICLR.

[15]  Shinnosuke Takamichi,et al.  Statistical Parametric Speech Synthesis Incorporating Generative Adversarial Networks , 2017, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[16]  J. Seok,et al.  Score-Guided Generative Adversarial Networks , 2020, Axioms.

[17]  Colin Raffel,et al.  Is Generator Conditioning Causally Related to GAN Performance? , 2018, ICML.

[18]  Hee-Deok Yang Restoring Raindrops Using Attentive Generative Adversarial Networks , 2021, Applied Sciences.

[19]  Wenling Liu,et al.  An Improved Method of Reservoir Facies Modeling Based on Generative Adversarial Networks , 2021, Energies.

[20]  Ching-Wei Wang,et al.  Deep Learning Fast Screening Approach on Cytological Whole Slides for Thyroid Cancer Diagnosis , 2021, Cancers.

[21]  Michael I. Jordan,et al.  Deep Generative Modeling for Single-cell Transcriptomics , 2018, Nature Methods.

[22]  Tom White,et al.  Generative Adversarial Networks: An Overview , 2017, IEEE Signal Processing Magazine.

[23]  Dominik Wolff,et al.  Multi-Asset Portfolio Optimization and Out-of-Sample Performance: An Evaluation of Black-Litterman, Mean Variance and Naïve Diversification Approaches , 2014 .

[24]  Abdulatif Alabdulatif,et al.  COVID-CGAN: Efficient Deep Learning Approach for COVID-19 Detection Based on CXR Images Using Conditional GANs , 2021, Applied Sciences.

[25]  Simon Osindero,et al.  Conditional Generative Adversarial Nets , 2014, ArXiv.

[26]  Jaakko Lehtinen,et al.  Progressive Growing of GANs for Improved Quality, Stability, and Variation , 2017, ICLR.

[27]  Vasile Palade,et al.  Generative Adversarial Network-Based Scheme for Diagnosing Faults in Cyber-Physical Power Systems , 2021, Sensors.

[28]  Jeff Donahue,et al.  Large Scale GAN Training for High Fidelity Natural Image Synthesis , 2018, ICLR.

[29]  J. L. Pedersen,et al.  Optimal mean-variance portfolio selection , 2017 .

[30]  Li Fei-Fei,et al.  Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[31]  Junhee Seok,et al.  Regularization Methods for Generative Adversarial Networks: An Overview of Recent Studies , 2020, ArXiv.

[32]  Kevin Smith,et al.  Bayesian Uncertainty Estimation for Batch Normalized Deep Networks , 2018, ICML.

[33]  Han Zhang,et al.  Self-Attention Generative Adversarial Networks , 2018, ICML.

[34]  Inbar Fijalkow,et al.  Deep Reinforcement Learning for Hybrid Energy Storage Systems: Balancing Lead and Hydrogen Storage , 2021, Energies.

[35]  Jean-Luc Dugelay,et al.  Face aging with conditional generative adversarial networks , 2017, 2017 IEEE International Conference on Image Processing (ICIP).

[36]  Lawrence Carin,et al.  Learning Structured Weight Uncertainty in Bayesian Neural Networks , 2017, AISTATS.

[37]  Philip H. S. Torr,et al.  Multi-agent Diverse Generative Adversarial Networks , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[38]  A. Comelli,et al.  Customized Efficient Neural Network for COVID-19 Infected Region Identification in CT Images , 2021, J. Imaging.

[39]  Gang Sun,et al.  Squeeze-and-Excitation Networks , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[40]  O. Sheils,et al.  Deep Learning of Histopathological Features for the Prediction of Tumour Molecular Genetics , 2021, Diagnostics.

[41]  Takeru Miyato,et al.  cGANs with Projection Discriminator , 2018, ICLR.

[42]  Blake Hannaford,et al.  Local Style Preservation in Improved GAN-Driven Synthetic Image Generation for Endoscopic Tool Segmentation , 2021, Sensors.

[43]  Jingcong Li,et al.  License Plate Image Reconstruction Based on Generative Adversarial Networks , 2021, Remote. Sens..

[44]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[45]  Vijay Vasudevan,et al.  Learning Transferable Architectures for Scalable Image Recognition , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[46]  Zhe Gan,et al.  Learning Weight Uncertainty with Stochastic Gradient MCMC for Shape Classification , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[47]  Zoubin Ghahramani,et al.  Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning , 2015, ICML.