Leveraging Sparse Features Learned from Natural Images for Seismic Understanding

Shafiq, M.A.; Prabhushankar, Mohit; AlRegib, Ghassan

doi:10.3997/2214-4609.201800737

Cited by 4 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This idea of N separate gradients to characterize data is not new. In Settles et al (2007), the authors construct positive and negative instance labels for a given input x in a binary decision setting. This is done to quantify uncertainty in an active learning setting.…”

Section: Discriminative Networkmentioning

confidence: 99%

“…Recently the generalization capabilities of neural networks has led to their widespread adoption in a number of computational fields. Neural networks have produced state-of-the-art results on multifarious data ranging from natural images (Krizhevsky et al, 2012 ), computed seismic (Shafiq M. A. et al, 2018 ; Shafiq M. et al, 2018 ), and biomedical images (Prabhushankar and AlRegib, 2021b ; Prabhushankar et al, 2022 ). In object recognition on Imagenet dataset (Deng et al, 2009 ), He et al ( 2016 ) surpassed the top five human accuracy of 94.9%.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Stochastic surprisal: An inferential measurement of free energy in neural networks

Prabhushankar

AlRegib²

2023

Front. Neurosci.

View full text Add to dashboard Cite

This paper conjectures and validates a framework that allows for action during inference in supervised neural networks. Supervised neural networks are constructed with the objective to maximize their performance metric in any given task. This is done by reducing free energy and its associated surprisal during training. However, the bottom-up inference nature of supervised networks is a passive process that renders them fallible to noise. In this paper, we provide a thorough background of supervised neural networks, both generative and discriminative, and discuss their functionality from the perspective of free energy principle. We then provide a framework for introducing action during inference. We introduce a new measurement called stochastic surprisal that is a function of the network, the input, and any possible action. This action can be any one of the outputs that the neural network has learnt, thereby lending stochasticity to the measurement. Stochastic surprisal is validated on two applications: Image Quality Assessment and Recognition under noisy conditions. We show that, while noise characteristics are ignored to make robust recognition, they are analyzed to estimate image quality scores. We apply stochastic surprisal on two applications, three datasets, and as a plug-in on 12 networks. In all, it provides a statistically significant increase among all measures. We conclude by discussing the implications of the proposed stochastic surprisal in other areas of cognitive psychology including expectancy-mismatch and abductive reasoning.

show abstract

Section: Discriminative Networkmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Stochastic surprisal: An inferential measurement of free energy in neural networks

Prabhushankar

AlRegib²

2023

Front. Neurosci.

View full text Add to dashboard Cite

show abstract

Reliable uncertainty estimation for seismic interpretation with prediction switches

Benkert

Prabhushankar

AlRegib

2022

Second International Meeting for Applied Geoscience &Amp; Energy

View full text Add to dashboard Cite

This paper presents a discussion on data selection for deep learning in the field of seismic interpretation. In order to achieve a robust generalization to the target volume, it is crucial to identify the specific samples are the most informative to the training process. The selection of the training set from a target volume is a critical factor in determining the effectiveness of the deep learning algorithm for interpreting seismic volumes. This paper proposes the inclusion of interpretation disagreement as a valuable and intuitive factor in the process of selecting training sets. The development of a novel data selection framework is inspired by established practices in seismic interpretation. The framework we have developed utilizes representation shifts to effectively model interpretation disagreement within neural networks. Additionally, it incorporates the disagreement measure to enhance attention towards geologically interesting regions throughout the data selection workflow. By combining this approach with active learning, a well-known machine learning paradigm for data selection, we arrive at a comprehensive and innovative framework for training set selection in seismic interpretation. In addition, we offer a specific implementation of our proposed framework, which we have named ATLAS. This implementation serves as a means for data selection. In this study, we present the results of our comprehensive experiments, which clearly indicate that ATLAS consistently surpasses traditional active learning frameworks in the field of seismic interpretation. Our findings reveal that ATLAS achieves improvements of up to 12% in mean intersection-over-union.

show abstract

Volumetric supervised contrastive learning for seismic semantic segmentation

Kiran

Prabhushankar

AlRegib

2022

Second International Meeting for Applied Geoscience &Amp; Energy

View full text Add to dashboard Cite

Leveraging Sparse Features Learned from Natural Images for Seismic Understanding

Cited by 4 publications

References 0 publications

Stochastic surprisal: An inferential measurement of free energy in neural networks

Stochastic surprisal: An inferential measurement of free energy in neural networks

Reliable uncertainty estimation for seismic interpretation with prediction switches

Volumetric supervised contrastive learning for seismic semantic segmentation

Contact Info

Product

Resources

About