Search

Your search keyword '"Sharma, Tilak"' showing total 742 results
Start Over Author "Sharma, Tilak"
742 results on '"Sharma, Tilak"'

2. Confidential and Protected Disease Classifier using Fully Homomorphic Encryption

Author

Malik, Aditya, Ratha, Nalini, Yalavarthi, Bharat, Sharma, Tilak, Kaushik, Arjun, and Jutla, Charanjit

Subjects
Computer Science - Cryptography and Security, Computer Science - Machine Learning
Abstract

With the rapid surge in the prevalence of Large Language Models (LLMs), individuals are increasingly turning to conversational AI for initial insights across various domains, including health-related inquiries such as disease diagnosis. Many users seek potential causes on platforms like ChatGPT or Bard before consulting a medical professional for their ailment. These platforms offer valuable benefits by streamlining the diagnosis process, alleviating the significant workload of healthcare practitioners, and saving users both time and money by avoiding unnecessary doctor visits. However, Despite the convenience of such platforms, sharing personal medical data online poses risks, including the presence of malicious platforms or potential eavesdropping by attackers. To address privacy concerns, we propose a novel framework combining FHE and Deep Learning for a secure and private diagnosis system. Operating on a question-and-answer-based model akin to an interaction with a medical practitioner, this end-to-end secure system employs Fully Homomorphic Encryption (FHE) to handle encrypted input data. Given FHE's computational constraints, we adapt deep neural networks and activation functions to the encryted domain. Further, we also propose a faster algorithm to compute summation of ciphertext elements. Through rigorous experiments, we demonstrate the efficacy of our approach. The proposed framework achieves strict security and privacy with minimal loss in performance.

Published
2024

17. Choose Your Neuron: Incorporating Domain Knowledge through Neuron-Importance

Author

Selvaraju, Ramprasaath R., Chattopadhyay, Prithvijit, Elhoseiny, Mohamed, Sharma, Tilak, Batra, Dhruv, Parikh, Devi, and Lee, Stefan

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Individual neurons in convolutional neural networks supervised for image-level classification tasks have been shown to implicitly learn semantically meaningful concepts ranging from simple textures and shapes to whole or partial objects - forming a "dictionary" of concepts acquired through the learning process. In this work we introduce a simple, efficient zero-shot learning approach based on this observation. Our approach, which we call Neuron Importance-AwareWeight Transfer (NIWT), learns to map domain knowledge about novel "unseen" classes onto this dictionary of learned concepts and then optimizes for network parameters that can effectively combine these concepts - essentially learning classifiers by discovering and composing learned semantic concepts in deep networks. Our approach shows improvements over previous approaches on the CUBirds and AWA2 generalized zero-shot learning benchmarks. We demonstrate our approach on a diverse set of semantic inputs as external domain knowledge including attributes and natural language captions. Moreover by learning inverse mappings, NIWT can provide visual and textual explanations for the predictions made by the newly learned classifiers and provide neuron names. Our code is available at https://github.com/ramprs/neuron-importance-zsl., Comment: In Proceedings of ECCV 2018

Published
2018

21. Wheat Quality Improvement for Micronutrients

Author

Bisht, Ashita, Kaur, Satveer, Sharma, Shivani, Bhandawat, Abhishek, Bhardwaj, Shubham, Garg, Monika, Pandey, Ajay Kumar, Bishnoi, Mahendra, Sharma, Tilak Raj, Roy, Joy K., Wani, Shabir H, editor, Mohan, Amita, editor, and Singh, Gyanendra Pratap, editor

Published
2021
Full Text
View/download PDF

33. SpeedFlower: a comprehensive speed breeding protocol for indica and japonica rice

Author

Kabade, Pramod Gorakhanath, primary, Dixit, Shilpi, additional, Singh, Uma Maheshwar, additional, Alam, Shamshad, additional, Bhosale, Sankalp, additional, Kumar, Sanjay, additional, Singh, Shravan Kumar, additional, Badri, Jyothi, additional, Varma, Nadimpalli Rama Gopala, additional, Chetia, Sanjay, additional, Singh, Rakesh, additional, Pradhan, Sharat Kumar, additional, Banerjee, Shubha, additional, Deshmukh, Rupesh, additional, Singh, Suresh Prasad, additional, Kalia, Sanjay, additional, Sharma, Tilak Raj, additional, Singh, Sudhanshu, additional, Bhardwaj, Hans, additional, Kohli, Ajay, additional, Kumar, Arvind, additional, Sinha, Pallavi, additional, and Singh, Vikas Kumar, additional

Published
2023
Full Text
View/download PDF

40. Oryza coarctata Roxb

Author

Chowrasia, Soni, Rawal, Hukam Chand, Mazumder, Abhishek, Gaikwad, Kishor, Sharma, Tilak Raj, Singh, Nagendra Kumar, Mondal, Tapan K., Kole, Chittaranjan, Series editor, Mondal, Tapan K., editor, and Henry, Robert J., editor

Published
2018
Full Text
View/download PDF

41. Choose Your Neuron: Incorporating Domain Knowledge Through Neuron-Importance

Author

R. Selvaraju, Ramprasaath, Chattopadhyay, Prithvijit, Elhoseiny, Mohamed, Sharma, Tilak, Batra, Dhruv, Parikh, Devi, Lee, Stefan, Hutchison, David, Series Editor, Kanade, Takeo, Series Editor, Kittler, Josef, Series Editor, Kleinberg, Jon M., Series Editor, Mattern, Friedemann, Series Editor, Mitchell, John C., Series Editor, Naor, Moni, Series Editor, Pandu Rangan, C., Series Editor, Steffen, Bernhard, Series Editor, Terzopoulos, Demetri, Series Editor, Tygar, Doug, Series Editor, Weikum, Gerhard, Series Editor, Ferrari, Vittorio, editor, Hebert, Martial, editor, Sminchisescu, Cristian, editor, and Weiss, Yair, editor

Published
2018
Full Text
View/download PDF

43. Wheat Quality Improvement for Micronutrients

Author

Bisht, Ashita, primary, Kaur, Satveer, additional, Sharma, Shivani, additional, Bhandawat, Abhishek, additional, Bhardwaj, Shubham, additional, Garg, Monika, additional, Pandey, Ajay Kumar, additional, Bishnoi, Mahendra, additional, Sharma, Tilak Raj, additional, and Roy, Joy K., additional

Published
2020
Full Text
View/download PDF

45. SpeedFlower: a comprehensive speed breeding protocol for indica and japonica rice.

Author

Kabade, Pramod Gorakhanath, Dixit, Shilpi, Singh, Uma Maheshwar, Alam, Shamshad, Bhosale, Sankalp, Kumar, Sanjay, Singh, Shravan Kumar, Badri, Jyothi, Varma, Nadimpalli Rama Gopala, Chetia, Sanjay, Singh, Rakesh, Pradhan, Sharat Kumar, Banerjee, Shubha, Deshmukh, Rupesh, Singh, Suresh Prasad, Kalia, Sanjay, Sharma, Tilak Raj, Singh, Sudhanshu, Bhardwaj, Hans, and Kohli, Ajay

Subjects
RICE breeding, RICE, LIGHT intensity, GIBBERELLIC acid, CLIMATE change
Abstract

Summary: To increase rice yields and feed billions of people, it is essential to enhance genetic gains. However, the development of new varieties is hindered by longer generation times and seasonal constraints. To address these limitations, a speed breeding facility has been established and a robust speed breeding protocol, SpeedFlower is developed that allows growing 4–5 generations of indica and/or japonica rice in a year. Our findings reveal that a high red‐to‐blue (2R > 1B) spectrum ratio, followed by green, yellow and far‐red (FR) light, along with a 24‐h long day (LD) photoperiod for the initial 15 days of the vegetative phase, facilitated early flowering. This is further enhanced by 10‐h short day (SD) photoperiod in the later stage and day and night temperatures of 32/30 °C, along with 65% humidity facilitated early flowering ranging from 52 to 60 days at high light intensity (800 μmol m−2 s−1). Additionally, the use of prematurely harvested seeds and gibberellic acid treatment reduced the maturity duration by 50%. Further, SpeedFlower was validated on a diverse subset of 198 rice accessions from 3K RGP panel encompassing all 12 distinct groups of Oryza sativa L. classes. Our results confirmed that using SpeedFlower one generation can be achieved within 58–71 days resulting in 5.1–6.3 generations per year across the 12 sub‐groups. This breakthrough enables us to enhance genetic gain, which could feed half of the world's population dependent on rice. We've developed a robust SpeedFlower protocol for rapid rice breeding, enabling 4–5 generations of indica and/or japonica rice annually. The SpeedFlower protocol was validated on 198 diverse rice accessions, representing all 12 sub‐groups of Oryza sativa L. With a timeframe of 58–71 days per generation, we achieved 5.1–6.3 generations per year. Therefore, SpeedFlower has shown a transformative potential in enhancing genetic gain with the pace of climate change. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

49. Development of genic-SSR markers by deep transcriptome sequencing in pigeonpea [Cajanus Cajan (L.) Millspaugh]

Author

Dutta, Sutapa, Kumawat, Giriraj, Singh, Bikram P, Gupta, Deepak K, Singh, Sangeeta, Dogra, Vivek, Gaikwad, Kishor, Sharma, Tilak R, Raje, Ranjeet S, Bandhopadhya, Tapas K, Datta, Subhojit, Singh, Mahendra N, Bashasab, Fakrudin, Kulwal, Pawan, Wanjari, KB, K Varshney, Rajeev, Cook, Douglas R, and Singh, Nagendra K

Abstract

Abstract Background Pigeonpea [Cajanus cajan (L.) Millspaugh], one of the most important food legumes of semi-arid tropical and subtropical regions, has limited genomic resources, particularly expressed sequence based (genic) markers. We report a comprehensive set of validated genic simple sequence repeat (SSR) markers using deep transcriptome sequencing, and its application in genetic diversity analysis and mapping. Results In this study, 43,324 transcriptome shotgun assembly unigene contigs were assembled from 1.696 million 454 GS-FLX sequence reads of separate pooled cDNA libraries prepared from leaf, root, stem and immature seed of two pigeonpea varieties, Asha and UPAS 120. A total of 3,771 genic-SSR loci, excluding homopolymeric and compound repeats, were identified; of which 2,877 PCR primer pairs were designed for marker development. Dinucleotide was the most common repeat motif with a frequency of 60.41%, followed by tri- (34.52%), hexa- (2.62%), tetra- (1.67%) and pentanucleotide (0.76%) repeat motifs. Primers were synthesized and tested for 772 of these loci with repeat lengths of ≥18 bp. Of these, 550 markers were validated for consistent amplification in eight diverse pigeonpea varieties; 71 were found to be polymorphic on agarose gel electrophoresis. Genetic diversity analysis was done on 22 pigeonpea varieties and eight wild species using 20 highly polymorphic genic-SSR markers. The number of alleles at these loci ranged from 4-10 and the polymorphism information content values ranged from 0.46 to 0.72. Neighbor-joining dendrogram showed distinct separation of the different groups of pigeonpea cultivars and wild species. Deep transcriptome sequencing of the two parental lines helped in silico identification of polymorphic genic-SSR loci to facilitate the rapid development of an intra-species reference genetic map, a subset of which was validated for expected allelic segregation in the reference mapping population. Conclusion We developed 550 validated genic-SSR markers in pigeonpea using deep transcriptome sequencing. From these, 20 highly polymorphic markers were used to evaluate the genetic relationship among species of the genus Cajanus. A comprehensive set of genic-SSR markers was developed as an important genomic resource for diversity analysis and genetic mapping in pigeonpea.

Published
2011

Catalog

Books, media, physical & digital resources
See catalog results