Search Results - "Humayun, Ahmed Imtiaz"

Towards Domain Invariant Heart Sound Abnormality Detection Using Learnable Filterbanks by Humayun, Ahmed Imtiaz, Ghaffarzadegan, Shabnam, Ansari, Md. Istiaq, Feng, Zhe, Hasan, Taufiq

“…Objective: Cardiac auscultation is the most practiced non-invasive and cost-effective procedure for the early diagnosis of heart diseases. While machine…”
Get full text

SplineCam: Exact Visualization and Characterization of Deep Network Geometry and Decision Boundaries by Humayun, Ahmed Imtiaz, Balestriero, Randall, Balakrishnan, Guha, Baraniuk, Richard

“…Current Deep Network (DN) visualization and inter-pretability methods rely heavily on data space visualizations such as scoring which dimensions of the data…”
Get full text

No More Than 6ft Apart: Robust K-Means via Radius Upper Bounds by Imtiaz Humayun, Ahmed, Balestriero, Randall, Kyrillidis, Anastasios, Baraniuk, Richard

“…Centroid based clustering methods such as k-means, k-medoids and k-centers are heavily applied as a go-to tool in exploratory data analysis. In many cases,…”
Get full text

Wearing A Mask: Compressed Representations of Variable-Length Sequences Using Recurrent Neural Tangent Kernels by Alemohammad, Sina, Babaei, Hossein, Balestriero, Randall, Cheung, Matt Y., Humayun, Ahmed Imtiaz, LeJeune, Daniel, Liu, Naiming, Luzi, Lorenzo, Tan, Jasper, Wang, Zichao, Baraniuk, Richard G.

“…High dimensionality poses many challenges to the use of data, from visualization and interpretation, to prediction and storage for historical preservation…”
Get full text

Polarity Sampling: Quality and Diversity Control of Pre-Trained Generative Networks via Singular Values by Humayun, Ahmed Imtiaz, Balestriero, Randall, Baraniuk, Richard

“…We present Polarity Sampling, a theoretically justified plug-and-play method for controlling the generation quality and diversity of any pre-trained deep…”
Get full text

Towards Domain Invariant Heart Sound Abnormality Detection using Learnable Filterbanks by Humayun, Ahmed Imtiaz, Ghaffarzadegan, Shabnam, Ansari, Md. Istiaq, Feng, Zhe, Hasan, Taufiq

“…IEEE Journal of Biomedical and Health Informatics 24 (2020) 2189 - 2198 Cardiac auscultation is the most practiced non-invasive and cost-effective procedure…”
Get full text

A Large Multi-Target Dataset of Common Bengali Handwritten Graphemes by Alam, Samiul, Reasat, Tahsin, Sushmit, Asif Shahriyar, Siddiquee, Sadi Mohammad, Rahman, Fuad, Hasan, Mahady, Humayun, Ahmed Imtiaz

“…Latin has historically led the state-of-the-art in handwritten optical character recognition (OCR) research. Adapting existing systems from Latin to…”
Get full text

Learning Front-end Filter-bank Parameters using Convolutional Neural Networks for Abnormal Heart Sound Detection by Humayun, Ahmed Imtiaz, Ghaffarzadegan, Shabnam, Feng, Zhe, Hasan, Taufiq

“…Automatic heart sound abnormality detection can play a vital role in the early diagnosis of heart diseases, particularly in low-resource settings. The…”
Get full text

An Ensemble of Transfer, Semi-supervised and Supervised Learning Methods for Pathological Heart Sound Classification by Humayun, Ahmed Imtiaz, Khan, Md. Tauhiduzzaman, Ghaffarzadegan, Shabnam, Feng, Zhe, Hasan, Taufiq

“…In this work, we propose an ensemble of classifiers to distinguish between various degrees of abnormalities of the heart using Phonocardiogram (PCG) signals…”
Get full text

Uniform Sampling From Deep Generative Network Manifolds by Humayun, Ahmed Imtiaz

“…Deep Generative Networks (DGNs) are extensively employed to approximate data manifolds and distributions. However, samples used to train such DGNs are often…”
Get full text

On the Geometry of Deep Learning by Balestriero, Randall, Humayun, Ahmed Imtiaz, Baraniuk, Richard

“…In this paper, we overview one promising avenue of progress at the mathematical foundation of deep learning: the connection between deep networks and function…”
Get full text

Deep Networks Always Grok and Here is Why by Humayun, Ahmed Imtiaz, Balestriero, Randall, Baraniuk, Richard

“…Grokking, or delayed generalization, is a phenomenon where generalization in a deep neural network (DNN) occurs long after achieving near zero training error…”
Get full text

Training Dynamics of Deep Network Linear Regions by Humayun, Ahmed Imtiaz, Balestriero, Randall, Baraniuk, Richard

“…The study of Deep Network (DN) training dynamics has largely focused on the evolution of the loss function, evaluated on or around train and test set data…”
Get full text

Polarity Sampling: Quality and Diversity Control of Pre-Trained Generative Networks via Singular Values by Humayun, Ahmed Imtiaz, Balestriero, Randall, Baraniuk, Richard

“…We present Polarity Sampling, a theoretically justified plug-and-play method for controlling the generation quality and diversity of pre-trained deep…”
Get full text

Learning Front-end Filter-bank Parameters using Convolutional Neural Networks for Abnormal Heart Sound Detection by Humayun, Ahmed Imtiaz, Ghaffarzadegan, Shabnam, Zhe Feng, Hasan, Taufiq

“…Automatic heart sound abnormality detection can play a vital role in the early diagnosis of heart diseases, particularly in low-resource settings. The…”
Get full text

MaGNET: Uniform Sampling from Deep Generative Network Manifolds Without Retraining by Humayun, Ahmed Imtiaz, Balestriero, Randall, Baraniuk, Richard

“…Deep Generative Networks (DGNs) are extensively employed in Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), and their variants to…”
Get full text

SplineCam: Exact Visualization and Characterization of Deep Network Geometry and Decision Boundaries by Humayun, Ahmed Imtiaz, Balestriero, Randall, Balakrishnan, Guha, Baraniuk, Richard

“…Current Deep Network (DN) visualization and interpretability methods rely heavily on data space visualizations such as scoring which dimensions of the data are…”
Get full text

Learning Transferable Features for Implicit Neural Representations by Vyas, Kushal, Humayun, Ahmed Imtiaz, Dashpute, Aniket, Baraniuk, Richard G, Veeraraghavan, Ashok, Balakrishnan, Guha

“…Implicit neural representations (INRs) have demonstrated success in a variety of applications, including inverse problems and neural rendering. An INR is…”
Get full text

Self-Improving Diffusion Models with Synthetic Data by Alemohammad, Sina, Humayun, Ahmed Imtiaz, Agarwal, Shruti, Collomosse, John, Baraniuk, Richard

“…The artificial intelligence (AI) world is running out of real data for training increasingly large generative models, resulting in accelerating pressure to…”
Get full text

Understanding the Local Geometry of Generative Model Manifolds by Humayun, Ahmed Imtiaz, Amara, Ibtihel, Schumann, Candice, Farnadi, Golnoosh, Rostamzadeh, Negar, Havaei, Mohammad

“…Deep generative models learn continuous representations of complex data manifolds using a finite number of samples during training. For a pre-trained…”
Get full text