Early Detection of Alzheimer’s Disease using Convolutional Neural Network Architecture

Kamath, Deepthi; Fathima, Misba Firdose; P, Monica K.; Mohanchandra, Kusuma

doi:10.36079/lamintang.ijai-0802.232

Cited by 4 publications

(4 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The idea of IRM and its variants are widely applied in many machine learning tasks (Sagawa et al, 2020;Zhang et al, 2020;Krueger et al, 2021;Lu et al, 2021) due to their seamless integration into pure prediction methods such as neural networks. However, there are few theoretical analyses and the performance improvement over the standard empirical risk minimization is not clear (Rosenfeld et al, 2021;Kamath et al, 2021). Our paper is the first to provide a thorough statistical analysis of invariance learning.…”

Section: Related Workmentioning

confidence: 95%

Environment Invariant Linear Least Squares

Fan¹,

Cong²,

Gu³

et al. 2023

Preprint

View full text Add to dashboard Cite

This paper considers a multiple environments linear regression model in which data from multiple experimental settings are collected. The joint distribution of the response variable and covariate may vary across different environments, yet the conditional expectation of y given the unknown set of important variables are invariant across environments. Such a statistical model is related to the problem of endogeneity, causal inference, and transfer learning. The motivation behind it is illustrated by how the goals of prediction and attribution are inherent in estimating the true parameter and the important variable set. We construct a novel environment invariant linear least squares (EILLS) objective function, a multiple-environment version of linear least squares that leverages the above conditional expectation invariance structure and heterogeneity among different environments to determine the true parameter. Our proposed method is applicable without any additional structural knowledge and can identify the true parameter under a near-minimal identification condition. We establish non-asymptotic 2 error bounds on the estimation error for the EILLS estimator in the presence of spurious variables. Moreover, we further show that the EILLS estimator is able to eliminate all endogenous variables and the 0 penalized EILLS estimator can achieve variable selection consistency in high-dimensional regimes. These nonasymptotic results demonstrate the sample efficiency of the EILLS estimator and its capability to circumvent the curse of endogeneity in an algorithmic manner without any prior structural knowledge.

show abstract

Section: Related Workmentioning

confidence: 95%

Environment Invariant Linear Least Squares

Fan¹,

Cong²,

Gu³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Despite the potential and popularity of IRL, plentiful followup studies unveiled IRLs' unreliability to learn invariant representation (Kamath et al 2021;Nagarajan, Andreassen, and Neyshabur 2020;Rosenfeld, Ravikumar, and Risteski 2020), in which the most notorious problem is probably the fake invariant effect . Particularly, given each environment factor to identify a specific spurious feature in a SCM, if the number of latent environment factors less than the capacity of spurious features, latent spurious correlation would pretend as an invarant part of the algorithm-recovered features recov-…”

Section: Fake Ood Invariant Effectmentioning

confidence: 99%

Diagnosing and Rectifying Fake OOD Invariance: A Restructured Causal Approach

Chen,

Zheng,

Lai

et al. 2024

AAAI

View full text Add to dashboard Cite

Invariant representation learning (IRL) encourages the prediction from invariant causal features to labels deconfounded from the environments, advancing the technical roadmap of out-of-distribution (OOD) generalization. Despite spotlights around, recent theoretical result verified that some causal features recovered by IRLs merely pretend domain-invariantly in the training environments but fail in unseen domains. The fake invariance severely endangers OOD generalization since the trustful objective can not be diagnosed and existing causal remedies are invalid to rectify. In this paper, we review a IRL family (InvRat) under the Partially and Fully Informative Invariant Feature Structural Causal Models (PIIF SCM /FIIF SCM) respectively, to certify their weaknesses in representing fake invariant features, then, unify their causal diagrams to propose ReStructured SCM (RS-SCM). RS-SCM can ideally rebuild the spurious and the fake invariant features simultaneously. Given this, we further develop an approach based on conditional mutual information with respect to RS-SCM, then rigorously rectify the spurious and fake invariant effects. It can be easily implemented by a small feature selection subnet introduced in the IRL family, which is alternatively optimized to achieve our goal. Experiments verified the superiority of our approach to fight against the fake invariant issue across a variety of OOD generalization benchmarks.

show abstract

“…Rojas-Carulla et al (2018) propose the framework of invariant risk minimization (IRM) in order to find invariant representations across multiple training environments. However, Kamath et al (2021) and Choe et al (2020) find that the sample version of IRM can fail to capture the invariance in empirical studies. For the purpose of domain generalization, Chen and Bühlmann (2020) propose new estimands with theoretical guarantees under linear structural equation models.…”

Section: Related Literaturementioning

confidence: 99%

Robust Low Transformed Multi-Rank Tensor Completion With Deep Prior Regularization for Multi-Dimensional Image Recovery

Qiu

Zhang

2023

IEEE Trans. Big Data

View full text Add to dashboard Cite

In conventional statistical and machine learning methods, it is typically assumed that the test data are identically distributed with the training data. However, this assumption does not always hold, especially in applications where the target population are not well-represented in the training data. This is a notable issue in health-related studies, where specific ethnic populations may be underrepresented, posing a significant challenge for researchers aiming to make statistical inferences about these minority groups. In this work, we present a novel approach to addressing this challenge in linear regression models. We organize the model parameters for all the subpopulations into a tensor. By studying a structured tensor completion problem, we can achieve robust domain generalization, i.e., learning about sub-populations with limited or no available data. Our method novelly leverages the structure of group labels and it can produce more reliable and interpretable generalization results. We establish rigorous theoretical guarantees for the proposed method and demonstrate its minimax optimality. To validate the effectiveness of our approach, we conduct extensive numerical experiments and a real data study focused on education level prediction for multiple ethnic groups, comparing our results with those obtained using other existing methods.

show abstract

Early Detection of Alzheimer’s Disease using Convolutional Neural Network Architecture

Cited by 4 publications

References 5 publications

Environment Invariant Linear Least Squares

Environment Invariant Linear Least Squares

Diagnosing and Rectifying Fake OOD Invariance: A Restructured Causal Approach

Robust Low Transformed Multi-Rank Tensor Completion With Deep Prior Regularization for Multi-Dimensional Image Recovery

Contact Info

Product

Resources

About