• Implementation of an accelerator for edge computing devices 

  Gupta, Garvit; Deb, Sujay (Advisor) (IIITD, 2021-05-10)

  Edge computing is a distributed computing paradigm that brings computation and data storage closer to the location where it is needed to improve response times and save bandwidth. Two important aspects of edge computing ...
• Semi Supervised Federated Learning with pseudo-labeling 

  Gupta, Kavya; Prasad, Ranjitha (Advisor) (IIIT-Delhi, 2024-03)

  In order to efficiently learn from small amount of labeled data, this study presents pseudo- labeling using semi-supervised learning in a federated setting (Pseudo-FedSSL), a novel approach to semi-supervised federated ...
• Design and resource optimization of sparse code multiple access-assisted communication systems 

  Chaturvedi, Saumya; Bohara, Vivek Ashok (Advisor); Srivastava, Anand (Advisor) (IIIT-Delhi, 2024-07)

  The evolution of next-generation communication systems, driven by applications like smart cities, factories of future, and autonomous vehicles, has led to a surge in communication devices and applications facilitated by ...
• Quality-of-service aware resource allocation for integrated fiber-wireless (FiWi) access networks 

  Gupta, Akshita; Bohara, Vivek Ashok (Advisor); Srivastava, Anand (Advisor) (IIIT-Delhi, 2024-09)

  This thesis aims to propose an efficient resource allocation framework to ensure the quality of service (QoS) to the users. The frameworks proposed in this dissertation can be efficiently utilized to provide QoS guarantees ...
• Task-boundary agnostic continuous federated learning using online variational bayes 

  Reddy, Shivakanth; Prasad, Ranjitha (advisor) (IIIT-Delhi, 2024-08-04)

  Federated learning (FL) is a privacy-preserving machine learning approach that enables the training of models across multiple decentralized edge devices without exchanging raw data. However, local models trained only on ...
• Accounting for the correlation between low-threshold and high-threshold transistors using analytical techniques 

  Pandey, Prashasti; Saurabh, Sneh (Advisor) (IIIT-Delhi, 2024-06-01)

  With the scaling of semiconductor technology nodes, the impact of process-induced variations has increased. Statistical static timing analysis accounts for global and local variations in the timing analysis. The present ...
• NORD-F : addressing near-oods for robust classification through disentanglement representation learning for fine grained datasets 

  Sharma, Ishika; Prasad, Ranjitha (advisor) (IIIT-Delhi, 2024-07-29)

  Out-of-Distribution (OoD) detection has emerged as a crucial aspect in machine learning, essential for ensuring the resilience and reliability of models deployed in real-world scenarios. Traditional methods excel at ...
• Asymmetric high-density low leakage SRAM cells 

  Shroti, Ajay; Grover, Anuj (Advisor) (IIIT-Delhi, 2024-05-15)

  Embedded memories occupy up to 70% of the area and account for 30-50% power consumption in advanced digital SoCs. A large part of this power is leakage power. Therefore, high-density, low-leakage SRAM cells are desirable. ...
• Subspace learning for person Re-identification 

  Roy, Neelabhro; Subramanyam, A V (Advisor) (IIIT-Delhi, 2019-11)

  Person Re-Identi cation (PRID) has been one of the most prominent problems in intelligent video surveillance in the recent past. PRID is the task of retrieving all the instances of a person given a single shot or a sequence ...
• Efficient surveillanve video compression using dictionary/transform learning 

  Nayeem, Mohammad; Subramanyam, A V (Advisor) (IIIT-Delhi, 2017-11-18)

  Techniques used for sparsifying the signal in dictionary or transform domain are quite popular in signal processing. In this work, we propose a method for e cient compression of surveillance videos. We observe that in these ...
• Reducing test time using regression algorithms in post silicon validation 

  Mamodia, Shivani; Subramanyam, A V (Advisor) (IIIT-Delhi, 2020-07-01)
• Unsupervised cross modality person Re-Identification 

  Gupta, Sagar; Subramanyam, A V (Advisor) (IIIT-Delhi, 2020-07-01)

  Unsupervised Person Re-Identi cation (Re-ID) su ers severely from the gap in the modality. Many factors pose a challenge to the task, including occlusions, lightning conditions, pose changes, among several others. Various ...
• Design thinking for social innovation: the tale of humankind 

  Gupta, Aniket; Grover, Anuj (Advisor); Sharma, Jyoti (Advisor) (IIIT-Delhi, 2023-11-29)
• Demonstration of federated averaging using zigbee and SDR 

  Singh, Monika; Prasad, Ranjitha (Advisor) (IIIT-Delhi, 2023-11-29)

  Wireless devices, including mobile phones, laptops, autonomous driving, UAT, etc., generate an enormous amount of local data, which could be employed to train machine learning models for decision-making and improve prediction ...
• TA allocation system 

  Sony, Atyant; Palia, Arnav Kumar; Bansal, Mohit; Gupta, Nikhil; Darak, Sumit Jagdish (Advisor) (IIIT-Delhi, 2023-11-29)

  This report addresses significant challenges in our academic institution's manual Teaching Assistant (TA) allocation process. The current system relies on time-consuming Excel sheets and email-based communication, leading ...
• Northeast states content(youtube) analysis and identification of misinformation spread through online social networks 

  Upadhyay, Saurav; Haripriya, Soibam (Advisor) (IIIT-Delhi, 2023-11-28)

  In recent year, due to the advancement in online social networks, possibility of spreading misinformation increases. Online Social Networks earlier seem to be safer path for sharing information and strengthen the community, ...
• Design and evaluating performance of hardware accelerators for implementation of neural networks 

  Marwah, Sahas; Dubey, Suyash Kumar; Grover, Anuj (Advisor) (2023-12)

  Neural networks have emerged as a powerful tool in machine learning and deep learning, showcasing remarkable capabilities in image recognition, natural language processing, and autonomous decision-making tasks. However, ...
• Acoustic cues for multilingual abuse detection 

  Thakran, Yash; Abrol, Vinayak (Advisor) (IIIT-Delhi, 2023-05-09)

  Abusive content detection in the spoken text can be addressed by performing Automatic Speech Recognition (ASR) and leveraging advancements in natural language processing. However, ASR models introduce latency and often ...
• Approximate computing as a means of fault tolerance in mWNoCs 

  Joshua, Massa; Deb, Sujay (Advisor) (IIIT-Delhi, 2023-10-29)

  In the realm of chiplet-based computing, the advent of Network-on-Chip (NoC) technology has brought forth remarkable opportunities to harness the potential of on-chip wireless communication. This report embarks on a ...
• Image generation using AI 

  Srivastava, Aryman; Dheeraj; Bagler, Ganesh (Advisor) (IIIT-Delhi, 2023-04-29)

  Deep learning involves training machines to understand patterns, classify objects, and predict outcomes. This has led to the emergence of various fields, including computer vision, natural language processing, speech ...

View more