Search Results for author:
Found 20 papers, 13 papers with code
Deep Networks Always Grok and Here is Why
Our local complexity measures the density of the so-called 'linear regions' (aka, spline partition regions) that tile the DNN input space, and serves as a utile progress measure for training.
Training Dynamics of Deep Network Linear Regions
First, we present a novel statistic that encompasses the local complexity (LC) of the DN based on the concentration of linear regions inside arbitrary dimensional neighborhoods around data points.
Self-Consuming Generative Models Go MAD
Seismic advances in generative AI algorithms for imagery, text, and other data types has led to the temptation to use synthetic data to train next-generation models.
OOD-Speech: A Large Bengali Speech Recognition Dataset for Out-of-Distribution Benchmarking
Our test dataset comprises 23. 03 hours of speech collected and manually annotated from 17 different sources, e. g., Bengali TV drama, Audiobook, Talk show, Online class, and Islamic sermons to name a few.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Abugida Normalizer and Parser for Unicode texts
This paper proposes two libraries to address common and uncommon issues with Unicode-based writing schemes for Indic languages.
BaDLAD: A Large Multi-Domain Bengali Document Layout Analysis Dataset
While strides have been made in deep learning based Bengali Optical Character Recognition (OCR) in the past decade, the absence of large Document Layout Analysis (DLA) datasets has hindered the application of OCR in document transcription, e. g., transcribing historical documents and newspapers.
SplineCam: Exact Visualization and Characterization of Deep Network Geometry and Decision Boundaries
In this paper, we go one step further by developing the first provably exact method for computing the geometry of a DN's mapping - including its decision boundary - over a specified region of the data space.
Bengali Common Voice Speech Dataset for Automatic Speech Recognition
Bengali is one of the most spoken languages in the world with over 300 million speakers globally.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
No More Than 6ft Apart: Robust K-Means via Radius Upper Bounds
We propose to remedy such a scenario by introducing a maximal radius constraint $r$ on the clusters formed by the centroids, i. e., samples from the same cluster should not be more than $2r$ apart in terms of $\ell_2$ distance.
Polarity Sampling: Quality and Diversity Control of Pre-Trained Generative Networks via Singular Values
We present Polarity Sampling, a theoretically justified plug-and-play method for controlling the generation quality and diversity of pre-trained deep generative networks DGNs).
Ranked #1 on
Image Generation
on LSUN Car 512 x 384
MaGNET: Uniform Sampling from Deep Generative Network Manifolds Without Retraining
Deep Generative Networks (DGNs) are extensively employed in Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), and their variants to approximate the data manifold and distribution.
Ranked #4 on
Image Generation
on FFHQ 1024 x 1024
Wearing a MASK: Compressed Representations of Variable-Length Sequences Using Recurrent Neural Tangent Kernels
High dimensionality poses many challenges to the use of data, from visualization and interpretation, to prediction and storage for historical preservation.
A Large Multi-Target Dataset of Common Bengali Handwritten Graphemes
We propose a labeling scheme based on graphemes (linguistic segments of word formation) that makes segmentation in-side alpha-syllabary words linear and present the first dataset of Bengali handwritten graphemes that are commonly used in an everyday context.
Towards Domain Invariant Heart Sound Abnormality Detection using Learnable Filterbanks
Cardiac auscultation is the most practiced non-invasive and cost-effective procedure for the early diagnosis of heart diseases.
Signal Processing
X-Ray Image Compression Using Convolutional Recurrent Neural Networks
To the best of our knowledge, this is the first reported evaluation on using a deep convolutional RNN for medical image compression.
End-to-end Sleep Staging with Raw Single Channel EEG using Deep Residual ConvNets
The experimental results demonstrate the superiority of the proposed network compared to the best existing method, providing a relative improvement in epoch-wise average accuracy of 6. 8% and 6. 3% on the household data and multi-source data, respectively.
AI Learns to Recognize Bengali Handwritten Digits: Bengali.AI Computer Vision Challenge 2018
Solving problems with Artificial intelligence in a competitive manner has long been absent in Bangladesh and Bengali-speaking community.
An Ensemble of Transfer, Semi-supervised and Supervised Learning Methods for Pathological Heart Sound Classification
In this work, we propose an ensemble of classifiers to distinguish between various degrees of abnormalities of the heart using Phonocardiogram (PCG) signals acquired using digital stethoscopes in a clinical setting, for the INTERSPEECH 2018 Computational Paralinguistics (ComParE) Heart Beats SubChallenge.
Learning Front-end Filter-bank Parameters using Convolutional Neural Networks for Abnormal Heart Sound Detection
In this work, we propound a novel CNN architecture that integrates the front-end bandpass filters within the network using time-convolution (tConv) layers, which enables the FIR filter-bank parameters to become learnable.
NumtaDB - Assembled Bengali Handwritten Digits
To benchmark Bengali digit recognition algorithms, a large publicly available dataset is required which is free from biases originating from geographical location, gender, and age.
