A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Published in IEEE International Symposium on Devices Circuits and Systems (ISDCS), 2018, 2018
🎯 The objective of this project is to utilize a LASER INDUCED BREAKDOWN SPECTROGRAPHY (LIBS) instrument for soil mineral composition analysis in agriculture, facilitated by an Android-controlled platform.
Recommended citation: https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=8379684
Published:
Published:
Published in arXiv, 2023
🎯 The objective of this work is to prevent the generation of outputs containing undesired features from a pre-trained GAN where the underlying training data set is inaccessible.
Recommended citation: https://arxiv.org/abs/2309.14054
Published in arXiv, 2023
🎯 The primary goal of this study is twofold: first, to elucidate the relationship between filtering and unlearning processes, and second, to formulate a methodology aimed at mitigating the display of undesirable outputs generated from models characterized as black-box systems.
Recommended citation: http://arxiv.org/abs/2312.14895
Published in arXiv, 2024
🎯 The principal aim of this study is to formulate a methodology tailored for the purposeful elimination of information linked to a specific class of data from a pre-trained classification network.
Recommended citation: https://arxiv.org/abs/2403.16246
Published in In Submission Phase, 2024
🎯 The primary aim of this study is to propose a mathematical definition of forgetting in ML models and develop methodologies for forgetting specific undesired concepts from pre-trained classification models
Recommended citation: https://openreview.net/forum?id=eTba2zVEdO#discussion
Published:
Published in NeurIPS 2024 Workshop SafeGenAi, 2024
🎯 The principal objective of this work is to propose a machine unlearning methodology that can prevent the generation of outputs containing undesired features from a pre-trained diffusion model
Recommended citation: https://openreview.net/forum?id=B2wDjiED9V
Page not found. Your pixels are in another canvas.
About me
This is a page not in th emain menu
Published:
This post accounts the non-academic books that I love reading during my free time. I mostly like reading non-fiction books with doses of fiction occassionally. Below are the books I have read over the years.
Published:
In the world of academia, accomplished researchers often appear as paragons of success, their profiles adorned with accolades and achievements. However, behind the facade of triumph, a less celebrated narrative exists—a story of relentless struggle and failure that is seldom shared. As a fellow young researcher, I’ve keenly experienced the weight of this unspoken reality, often feeling isolated in my struggles. The purpose of this blog is to remind myself of my failures and also to make upcoming young researchers aware about the struggle. And Yes!! The struggle is real (atleast for me).
Published:
Over the past century, the field of artificial intelligence (AI) has experienced remarkable progress, primarily driven by the aspiration to enable machines to learn in a manner akin to humans. This pursuit has been rooted in a fundamental question: “how” can machines be effectively trained to perform specific tasks? It seems like the answer is the optimization of some specific loss functions, typically relying on carefully curated datasets.
Generative Models output unwanted and even harmful images. To tackle this problem recent line of works explores how to unlearn so that it stops generate these output. On the other hand when these models are used as Block-Box(i.e. the models architechture, parameters and underlying dataset are unknown) in several other downstream task. In this situation unlearning the model becomes harder and only blocking gives pratical way to tackle the problem of stop showing undesired outputs. In this work we devise a way to block the generative models outputs in latent space.
Due to data bias and undesired data present in the dataset, generative models output unintended output which are harmful. To tackle this problem, we unlearn the generative models with the help of the user feedback. In our work using the feedback from the user we try to adapt our GAN so that it only produces the unintened images(negetive images). From there we try to purturb out initial model in such a way that it remain far from adapted model in parameter space.
Published in IEEE International Symposium on Devices Circuits and Systems (ISDCS), 2018, 2018
🎯 The objective of this project is to utilize a LASER INDUCED BREAKDOWN SPECTROGRAPHY (LIBS) instrument for soil mineral composition analysis in agriculture, facilitated by an Android-controlled platform.
Recommended citation: https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=8379684
Published in arXiv, 2023
🎯 The objective of this work is to prevent the generation of outputs containing undesired features from a pre-trained GAN where the underlying training data set is inaccessible.
Recommended citation: https://arxiv.org/abs/2309.14054
Published in arXiv, 2023
🎯 The primary goal of this study is twofold: first, to elucidate the relationship between filtering and unlearning processes, and second, to formulate a methodology aimed at mitigating the display of undesirable outputs generated from models characterized as black-box systems.
Recommended citation: http://arxiv.org/abs/2312.14895
Published in arXiv, 2024
🎯 The principal aim of this study is to formulate a methodology tailored for the purposeful elimination of information linked to a specific class of data from a pre-trained classification network.
Recommended citation: https://arxiv.org/abs/2403.16246
Published in In Submission Phase, 2024
🎯 The primary aim of this study is to propose a mathematical definition of forgetting in ML models and develop methodologies for forgetting specific undesired concepts from pre-trained classification models
Recommended citation: https://openreview.net/forum?id=eTba2zVEdO#discussion
Published in NeurIPS 2024 Workshop SafeGenAi, 2024
🎯 The principal objective of this work is to propose a machine unlearning methodology that can prevent the generation of outputs containing undesired features from a pre-trained diffusion model
Recommended citation: https://openreview.net/forum?id=B2wDjiED9V
Published:
Published:
Graduate Course, ISI & IISc, 2022
📌 Logistics: Lecture notes consists of materials from my coursework both at ISI and IISc.
Graduate Course, ISI & IISc, 2022
📌 Logistics: Lecture notes consists of materials from my coursework both at ISI and IISc. The course notes are in preperation will be posted soon.
Graduate Course, ISI & IISc, 2022
📌 Logistics: Lecture notes consists of materials from my coursework both at ISI and IISc.
Graduate Course, IISc, 2022
📌 Logistics: Lecture notes consists of materials from my coursework both at IISc.
Graduate Course, IISc, 2022
📌 Logistics: Lecture notes consists of materials from my coursework at IISc.
Graduate Course, IISc, 2023
📌 Logistics: These are self prepared notes required for my research on Differential Privacy.
Graduate Course, IISc, 2023
📌 Logistics: Lecture notes consists of materials from my coursework at IISc.
Graduate Course, IISc, 2023
📌 Logistics: These course notes are from my coursework at ISI and IISc. The course notes are in preperation will be posted soon.
Graduate Course, IISc, 2023
📌 Logistics: These course notes are from my coursework at ISI and IISc. More course notes are in preperation will be posted soon.
Graduate Course, IISc, 2024
📌 Logistics: Lecture notes consists of materials from my coursework at IISc.
Graduate Course, IISc, 2024
Graduate Course, IISc, 2024
📌 Logistics: This is a self-taught course. The topics are designed by myself mostly following the book: Algorithmic learning in a random world by V.Vovk, A.Gammerman, and G.Shafer.
Graduate Course, IISc, 2024
📌 Logistics: This is a self-taught course. The topics are designed by myself mostly following the book: Information Theory: From Coding to Learning by Y. Polyanskiy and Y. Wu.