About
Enkrypt AI: Accelerating generative AI adoption - Building best in class generative AI…
Activity
-
It's time! We've reached the phase of the OWASP Top 10 For Large Language Model Applications Version 2 roadmap, where we're accepting new entry…
It's time! We've reached the phase of the OWASP Top 10 For Large Language Model Applications Version 2 roadmap, where we're accepting new entry…
Liked by Prashanth Harshangi
-
3AI Holding has formed a strategic partnership with SML India to launch Hanooman, a Gen AI Platform. As a Gen AI platform, HANOOMAN. AI aims to make…
3AI Holding has formed a strategic partnership with SML India to launch Hanooman, a Gen AI Platform. As a Gen AI platform, HANOOMAN. AI aims to make…
Liked by Prashanth Harshangi
-
7 years of fostering innovation, 7 years of empowering startups, 7 years of excellence! We are thrilled to announce that NetApp Excellerator has…
7 years of fostering innovation, 7 years of empowering startups, 7 years of excellence! We are thrilled to announce that NetApp Excellerator has…
Liked by Prashanth Harshangi
Experience
Education
Publications
-
Breast Cancer classification using Committee Machines
IEEE International Conference on Electronic Design and Signal Processing(ICEDSP09)
-
How can systems learn from each other?
17th Yale Workshop on Adaptive and Learning Systems
-
Robustness of a face-recognition technique based on support vector machines
ICTACT Journal On Image And Video Processing
-
Simultaneous Identification of Multiple LTI Plants Using Multiple Models, Switching and Tuning
-
The multiple models, switching, and tuning methodology is used in this paper to identify simultaneously multiple linear time-invariant (LTI) plants. Two model assignment strategies are also presented. These strategies cause the models to organize themselves so that at any given instant only one model adapts to each plant. The choice of the assignment strategy and the performance criteria play an important role in the manner of both the convergence and the switching between models.
-
Support vector machine based face recognition
National Conference on Signal and Image Processing Applications
-
Unstable systems stabilizing each other through adaptation
-
An asymptotically stable reference model plays a crucial role in the entire literature on adaptive systems. Given a plant with unknown parameters, the objective is to adapt the parameters of a controller so that the behavior of the controlled plant emulates that of the reference model in some sense. This paper addresses the following question, which is markedly different from that encountered in conventional adaptive control: “Can two or more unstable plants adaptively stabilize each other? ”…
An asymptotically stable reference model plays a crucial role in the entire literature on adaptive systems. Given a plant with unknown parameters, the objective is to adapt the parameters of a controller so that the behavior of the controlled plant emulates that of the reference model in some sense. This paper addresses the following question, which is markedly different from that encountered in conventional adaptive control: “Can two or more unstable plants adaptively stabilize each other? ”. This is because neither system has a stable model to emulate, and each depends upon the other to stabilize itself. It is not surprising that this seemingly innocuous question has far reaching implications in widely different fields such as biology, psychology, economics and robotics, where it is found to arise frequently.
-
Unstable systems stabilizing each other through adaptation - part II
IEEE
It is now well realized [1] that two unstable dynamical systems, attempting to stabilize each other using the error between their outputs for adjusting their parameters, may not always succeed. The fact that adaptation may result in instability makes the mathematical problem a very interesting one. Since similar problems are arising in many other branches of science (e.g psychology, biology, medicine etc), obtaining precisely the conditions under which stability is achieved is also assuming…
It is now well realized [1] that two unstable dynamical systems, attempting to stabilize each other using the error between their outputs for adjusting their parameters, may not always succeed. The fact that adaptation may result in instability makes the mathematical problem a very interesting one. Since similar problems are arising in many other branches of science (e.g psychology, biology, medicine etc), obtaining precisely the conditions under which stability is achieved is also assuming greater importance. This paper may be considered as a first attempt to discuss the many aspects of this intriguing and difficult problem. Work carried out during the past year has shown that the interaction of two n th order systems, results in a 4n th order differential equation, whose stability has to be investigated. Even in the simple case when n = 2, determining necessary and sufficient conditions for stability is a formidable undertaking. However, through extensive simulation studies and the theoretical analysis of special cases suggested by them, numerous insights have been obtained. The objective of this paper is to convey these insights, and discuss wherever possible, their implications to higher order systems.
Patents
-
Dimensionality reduction in Bayesian Optimization using Stacked Autoencoders
Issued 15/662,917
The present embodiments relate to reducing the input dimensions to a machine-based Bayesian Optimization using stacked autoencoders. By way of introduction, the present embodiments described below include apparatuses and methods for pre-processing a digital input to a machine-based Bayesian Optimization to a lower the dimensional space of the input, thereby lowering the bounds of the Bayesian optimization. The output of the Bayesian Optimization is then projected back into the original…
The present embodiments relate to reducing the input dimensions to a machine-based Bayesian Optimization using stacked autoencoders. By way of introduction, the present embodiments described below include apparatuses and methods for pre-processing a digital input to a machine-based Bayesian Optimization to a lower the dimensional space of the input, thereby lowering the bounds of the Bayesian optimization. The output of the Bayesian Optimization is then projected back into the original dimensional space to determine input and output values in the original dimensional apace. As such, the optimization is performed by the machine in a lower dimension using the stacked autoencoder to constrain the input dimensions to the optimization.
More activity by Prashanth
Applications and workloads need intelligent data & optimized infrastructures, attend this session to learn how NetApp's public cloud services is…
Liked by Prashanth Harshangi
Really enjoyed talking with Chris Mellor about NetApp's vision for intelligent data infrastructure to support this era of AI.
Liked by Prashanth Harshangi
🌟 Exciting News! Join Us for Project Tailwind's AI Product Management MasterClass! 🚀 Hey LinkedIn Fam! 🌟 Don't miss out on our FREE online…
Liked by Prashanth Harshangi
People also viewed
Explore collaborative articles
We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.
Explore More