Zobrazeno 1 - 10
of 238
pro vyhledávání: '"Sastry, PS"'
Convolutional Neural Networks (CNNs) are very effective for many pattern recognition tasks. However, training deep CNNs needs extensive computation and large training data. In this paper we propose Bank of Filter-Trees (BFT) as a trans- fer learning
Externí odkaz:
http://arxiv.org/abs/1711.09648
Autor:
Shah Shesha, Sastry PS
Publikováno v:
EURASIP Journal on Advances in Signal Processing, Vol 2007, Iss 1, p 086064 (2007)
We present a motion detection algorithm which detects direction of motion at sufficient number of points and thus segregates the edge image into clusters of coherently moving points. Unlike most algorithms for motion analysis, we do not estimate magn
Externí odkaz:
https://doaj.org/article/947b0360476b447fb7d48d02c4676a5e
Autor:
Vijayadeep C, Sastry Ps
Publikováno v:
Journal of Bioremediation & Biodegradation.
Over the past century, unrestricted mining, extensive industrialization, modern agricultural practices and faulty waste disposal methods have resulted in the release of unprecedented levels of toxic heavy metals like Cd, Hg, Ag, Sn, Pb, Cu, Co, Mn, Z
Autor:
Manwani, Naresh, Sastry, PS
Publikováno v:
IndraStra Global.
In this paper we propose a new algorithm for learning polyhedral classifiers. In contrast to existing methods for learning polyhedral classifier which solve a constrained optimization problem, our method solves an unconstrained optimization problem.
Publikováno v:
IndraStra Global.
Publikováno v:
IndraStra Global.
Autor:
Sastry, PS, Unnikrishnan, KP
Publikováno v:
IndraStra Global.
Publikováno v:
IndraStra Global.
A method, system, and computer program product for fault data correlation in a diagnostic system are provided. The method includes receiving the fault data including a plurality of faults collected over a period of time, and identifying a plurality o
Autor:
Shah, Shesha, Sastry, PS
Publikováno v:
IndraStra Global.
We present a motion detection algorithm which detects direction of motion at sufficient number of points and thus segregates the edge image into clusters of coherently moving points. Unlike most algorithms for motion analysis, we do not estimate magn
Publikováno v:
IndraStra Global.
A new automatic generation controller (AGC) design approach, adopting reinforcement learning (RL) techniques, was recently pro- posed [1]. In this paper we demonstrate the design and performance of controllers based on this RL approach for automatic