15 citations · 38 across the 17 of their papers we have counts for
17 papers
Proof-of-Perception: Certified Tool-Using Multimodal Reasoning with Compositional Conformal Guarantees
Arya Fayyazi, Haleh Akrami
We present Proof-of-Perception (PoP), a tool-using framework that casts multimodal reasoning as an executable graph with explicit reliability guarantees. Each perception or logic n…
Modeling and Reversing Brain Lesions Using Diffusion Models
Omar Zamzam, Haleh Akrami, Anand Joshi +1
Brain lesions are abnormalities or injuries in brain tissue that are often detectable using magnetic resonance imaging (MRI), which reveals structural changes in the affected areas…
Generalizable Representation Learning for fMRI-based Neurological Disorder Identification
Wenhui Cui, Haleh Akrami, Anand A. Joshi +1
Despite the impressive advances achieved using deep learning for functional brain activity analysis, the heterogeneity of functional patterns and the scarcity of imaging data still…
Meta Transfer of Self-Supervised Knowledge: Foundation Model in Action for Post-Traumatic Epilepsy Prediction
Wenhui Cui, Haleh Akrami, Ganning Zhao +2
Despite the impressive advancements achieved using deep-learning for functional brain activity analysis, the heterogeneity of functional patterns and scarcity of imaging data still…
Learning A Disentangling Representation For PU Learning
Omar Zamzam, Haleh Akrami, Mahdi Soltanolkotabi +1
In this paper, we address the problem of learning a binary (positive vs. negative) classifier given Positive and Unlabeled data commonly referred to as PU learning. Although rudime…
Beta quantile regression for robust estimation of uncertainty in the presence of outliers
Haleh Akrami, Omar Zamzam, Anand Joshi +2
Quantile Regression (QR) can be used to estimate aleatoric uncertainty in deep neural networks and can generate prediction intervals. Quantifying uncertainty is particularly import…
Toward Improved Generalization: Meta Transfer of Self-supervised Knowledge on Graphs
Wenhui Cui, Haleh Akrami, Anand A. Joshi +1
Despite the remarkable success achieved by graph convolutional networks for functional brain activity analysis, the heterogeneity of functional patterns and the scarcity of imaging…
Speech MOS multi-task learning and rater bias correction
Haleh Akrami, Hannes Gamper
Perceptual speech quality is an important performance metric for teleconferencing applications. The mean opinion score (MOS) is standardized for the perceptual evaluation of speech…
Learning From Positive and Unlabeled Data Using Observer-GAN
Omar Zamzam, Haleh Akrami, Richard Leahy
The problem of learning from positive and unlabeled data (A.K.A. PU learning) has been studied in a binary (i.e., positive versus negative) classification setting, where the input…
Learning from imperfect training data using a robust loss function: application to brain image segmentation
Haleh Akrami, Wenhui Cui, Anand A Joshi +1
Segmentation is one of the most important tasks in MRI medical image analysis and is often the first and the most critical step in many clinical applications. In brain MRI analysis…
Semi-supervised Learning using Robust Loss
Wenhui Cui, Haleh Akrami, Anand A. Joshi +1
The amount of manually labeled data is limited in medical applications, so semi-supervised learning and automatic labeling strategies can be an asset for training deep neural netwo…
Deep Quantile Regression for Uncertainty Estimation in Unsupervised and Supervised Lesion Detection
Haleh Akrami, Anand Joshi, Sergul Aydore +1
Despite impressive state-of-the-art performance on a wide variety of machine learning tasks, deep learning methods can produce over-confident predictions, particularly with limited…
fMRI-Kernel Regression: A Kernel-based Method for Pointwise Statistical Analysis of rs-fMRI for Population Studies
Anand A. Joshi, Soyoung Choi, Haleh Akrami +1
Due to the spontaneous nature of resting-state fMRI (rs-fMRI) signals, cross-subject comparison and therefore, group studies of rs-fMRI are challenging. Most existing group compari…
Addressing Variance Shrinkage in Variational Autoencoders using Quantile Regression
Haleh Akrami, Anand A. Joshi, Sergul Aydore +1
Estimation of uncertainty in deep learning models is of vital importance, especially in medical imaging, where reliance on inference without taking into account uncertainty could l…
Robust Variational Autoencoder for Tabular Data with Beta Divergence
Haleh Akrami, Sergul Aydore, Richard M. Leahy +1
We propose a robust variational autoencoder with divergence for tabular data (RTVAE) with mixed categorical and continuous features. Variational autoencoders (VAE) and their va…
A Pre-defined Sparse Kernel Based Convolution for Deep CNNs
Souvik Kundu, Saurav Prakash, Haleh Akrami +2
The high demand for computational and storage resources severely impede the deployment of deep convolutional neural networks (CNNs) in limited-resource devices. Recent CNN architec…
Robust Variational Autoencoder
Haleh Akrami, Anand A. Joshi, Jian Li +2
Machine learning methods often need a large amount of labeled training data. Since the training data is assumed to be the ground truth, outliers can severely degrade learned repres…