no code implementations • 11 Apr 2025 • Kundan Kumar, Muhammad Iqbal, Simo Särkkä
Remote state estimation in cyber-physical systems is often vulnerable to cyber-attacks due to wireless connections between sensors and computing units.
no code implementations • 22 Jan 2025 • Muhammad Iqbal, Kundan Kumar, Simo Särkkä
The DKF problem is formulated within a distributed optimization framework, where coupling constraints require the exchange of local state and covariance updates between neighboring nodes to achieve consensus.
no code implementations • 12 Jan 2025 • Rohit Kumar Singh, Kundan Kumar, Shovan Bhaumik
This work introduces the Gaussian integration to address a smoothing problem of a nonlinear stochastic state space model.
4 code implementations • NeurIPS 2023 • Rithesh Kumar, Prem Seetharaman, Alejandro Luebs, Ishaan Kumar, Kundan Kumar
Language models have been successfully used to model natural signals, such as images, speech, and music.
no code implementations • 15 May 2023 • Shreya Das, Kundan Kumar, Shovan Bhaumik
Both adaptive filtering techniques are implemented using the traditional Gaussian approximate filters and are applied to a bearings-only tracking problem illustrated with moderately nonlinear and highly nonlinear scenarios to track a target following a nearly straight line path.
no code implementations • 18 Mar 2022 • Kundan Kumar, Sumanshu Agarwal
We validated the proposed method on retinal fundus images from the DRIVE database.
no code implementations • 18 Mar 2022 • Tithi Parna Das, Sheetal Praharaj, Sarita Swain, Sumanshu Agarwal, Kundan Kumar
In the medical domain, different computer-aided diagnosis systems have been proposed to extract blood vessels from retinal fundus images for the clinical treatment of vascular diseases.
no code implementations • 28 Feb 2022 • Jiztom Kavalakkatt Francis, Chandan Kumar, Jansel Herrera-Gerena, Kundan Kumar, Matthew J Darr
We propose a deep learning methodology for multivariate regression that is based on pattern recognition that triggers fast learning over sensor data.
1 code implementation • 21 Oct 2021 • Ho-Hsiang Wu, Prem Seetharaman, Kundan Kumar, Juan Pablo Bello
We propose Wav2CLIP, a robust audio representation learning method by distilling from Contrastive Language-Image Pre-training (CLIP).
1 code implementation • ICLR 2022 • Max Morrison, Rithesh Kumar, Kundan Kumar, Prem Seetharaman, Aaron Courville, Yoshua Bengio
We show that simple pitch and periodicity conditioning is insufficient for reducing this error relative to using autoregression.
no code implementations • 22 Oct 2020 • Rithesh Kumar, Kundan Kumar, Vicki Anand, Yoshua Bengio, Aaron Courville
In this paper, we propose NU-GAN, a new method for resampling audio from lower to higher sampling rates (upsampling).
no code implementations • 26 Oct 2019 • Debojyoti Mallick, Kundan Kumar, Sumanshu Agarwal
Blindness in diabetic patients caused by retinopathy (characterized by an increase in the diameter and new branches of the blood vessels inside the retina) is a grave concern.
21 code implementations • NeurIPS 2019 • Kundan Kumar, Rithesh Kumar, Thibault de Boissiere, Lucas Gestin, Wei Zhen Teoh, Jose Sotelo, Alexandre de Brebisson, Yoshua Bengio, Aaron Courville
In this paper, we show that it is possible to train GANs reliably to generate high quality coherent waveforms by introducing a set of architectural changes and simple training techniques.
no code implementations • 12 Aug 2019 • Kundan Kumar, Debashisa Samal, Suraj
In this paper, we suggest a new unsupervised retinal blood vessel segmentation approach using top-hat transformation, contrast-limited adaptive histogram equalization (CLAHE), and 2-D Gabor wavelet filters.
no code implementations • 27 Sep 2018 • Chin-wei Huang, Faruk Ahmed, Kundan Kumar, Alexandre Lacoste, Aaron Courville
Probability distillation has recently been of interest to deep learning practitioners as it presents a practical solution for sampling from autoregressive models for deployment in real-time applications.
no code implementations • 23 May 2018 • Chetan Singh Thakur, Jamal Molin, Gert Cauwenberghs, Giacomo Indiveri, Kundan Kumar, Ning Qiao, Johannes Schemmel, Runchun Wang, Elisabetta Chicca, Jennifer Olson Hasler, Jae-sun Seo, Shimeng Yu, Yu Cao, André van Schaik, Ralph Etienne-Cummings
Neuromorphic engineering (NE) encompasses a diverse range of approaches to information processing that are inspired by neurobiological systems, and this feature distinguishes neuromorphic systems from conventional computing systems.
1 code implementation • 6 Dec 2017 • Rithesh Kumar, Jose Sotelo, Kundan Kumar, Alexandre de Brebisson, Yoshua Bengio
We present ObamaNet, the first architecture that generates both audio and synchronized photo-realistic lip-sync videos from any new text.
4 code implementations • 22 Dec 2016 • Soroush Mehri, Kundan Kumar, Ishaan Gulrajani, Rithesh Kumar, Shubham Jain, Jose Sotelo, Aaron Courville, Yoshua Bengio
In this paper we propose a novel model for unconditional audio generation based on generating one audio sample at a time.
Ranked #1 on
Speech Synthesis
on Blizzard Challenge 2013
no code implementations • 19 Dec 2016 • Mihir Mongia, Kundan Kumar, Akram Erraqabi, Yoshua Bengio
Recent work in the literature has shown experimentally that one can use the lower layers of a trained convolutional neural network (CNN) to model natural textures.
1 code implementation • 15 Nov 2016 • Ishaan Gulrajani, Kundan Kumar, Faruk Ahmed, Adrien Ali Taiga, Francesco Visin, David Vazquez, Aaron Courville
Natural image modeling is a landmark challenge of unsupervised learning.