Zobrazeno 1 - 10
of 13
pro vyhledávání: '"Harshvardhan Sikka"'
Autor:
Harshvardhan Sikka
The classification tasks outlined in this report make use of 2 distinct datasets, the Wine Type and Quality Classification dataset and the Car evaluation dataset, both sourced from Kaggle. These datasets were chosen in particular for their differing
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::440192a34789c5eaf185df84e3ba728f
https://doi.org/10.31219/osf.io/u8x9d
https://doi.org/10.31219/osf.io/u8x9d
Autor:
Harshvardhan Sikka
This report is comprised of 5 main sections. The first focuses on the analysis of 2 Clustering Algorithms, KMeans and Expectation Maximization on the Wine Quality and Car Evaluation Datasets, which are motivated as interesting problems below. Followi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7f1f6effd6b65ccc49e278162d01a2ac
https://doi.org/10.31219/osf.io/9d4tg
https://doi.org/10.31219/osf.io/9d4tg
Autor:
Harshvardhan Sikka
This report is comprised of 2 sections. The first focuses on the analysis of three optimization problem domains that highlight the strengths of local random search algorithms. Algorithms implemented and analyzed include Randomized Hill Climbing (RHC)
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b61c760a6fb466f691d99062a4f167af
https://doi.org/10.31219/osf.io/yshpr
https://doi.org/10.31219/osf.io/yshpr
Production prediction is of high interest and relevance for dental practices. Forecasting future production accurately allows the coordination of business and supply chain logistics. Following a phase of initial explorations and considerations with r
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e28e0b477a924f3238da6f1745eeabde
https://doi.org/10.31219/osf.io/rbmc8
https://doi.org/10.31219/osf.io/rbmc8
Autor:
Sridhar Venkatesan, Harshvardhan Sikka, Rauf Izmailov, Ritu Chadha, Alina Oprea, Michael J. de Lucia
Publikováno v:
MILCOM 2021 - 2021 IEEE Military Communications Conference (MILCOM).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2a02e32f3badd8667c9e68496dee95db
https://doi.org/10.1109/milcom52596.2021.9652916
https://doi.org/10.1109/milcom52596.2021.9652916
Autor:
Harshvardhan Sikka, Sidhdharth Sikka
Publikováno v:
Lecture Notes in Networks and Systems ISBN: 9783030801250
Autonomous spacecraft maneuver planning using an evolutionary computing approach is investigated. Simulated satellites were placed into four different initial orbits. Each was allowed a string of thirty delta-v impulse maneuvers in six cartesian dire
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ee3c270ff807ac425d297d72bacb4e38
https://doi.org/10.1007/978-3-030-80126-7_68
https://doi.org/10.1007/978-3-030-80126-7_68
Publikováno v:
Lecture Notes in Networks and Systems ISBN: 9783030801250
Understanding the learning dynamics of deep neural networks is of significant interest to the research community as it can provide insights into the black box nature of neural nets. In this work, we conduct a study which analyzes layer-wise learning
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1d967a995232a8bfe37315d6f29ad11f
https://doi.org/10.1007/978-3-030-80126-7_48
https://doi.org/10.1007/978-3-030-80126-7_48
Interpreting the learning dynamics of neural networks can provide useful insights into how networks learn and the development of better training and design approaches. We present an approach to interpret learning in neural networks by measuring relat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2e64fe724665ce634f539c3439f453bd
Many real world prediction problems involve structured tasks across multiple modalities. We propose to extend previous work in modular meta learning to the multimodal setting. Specifically, we present an algorithmic approach to apply task aware modul
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d63bf58679770413049f55681e1c290d
https://doi.org/10.31219/osf.io/6ek2b
https://doi.org/10.31219/osf.io/6ek2b
In this paper we measure the effectiveness of $\epsilon$-Differential Privacy (DP) when applied to medical imaging. We compare two robust differential privacy mechanisms: Local-DP and DP-SGD and benchmark their performance when analyzing medical imag
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::71a6e023e901461d63f15a12ec55d83d
http://arxiv.org/abs/2005.13099
http://arxiv.org/abs/2005.13099