http://repository.iiitd.edu.in/xmlui/handle/123456789/928 2026-09-03T09:26:53Z 2026-09-03T09:26:53Z Gupta, Anmol Gupta, Bhavya Bagler, Bagler, Ganesh (Advisor) http://repository.iiitd.edu.in/xmlui/handle/123456789/2083 2026-09-03T06:19:11Z 2024-12-08T00:00:00Z

Title: RecipeGPT implementation Authors: Gupta, Anmol; Gupta, Bhavya; Bagler, Bagler, Ganesh (Advisor) Abstract: The culinary domain offers significant opportunities for leveraging AI to simplify and enhance recipe-related interactions. This project focuses on developing an intelligent recipe chatbot that performs two primary tasks: (1) generating cooking instructions from a list of ingredients, and (2) predicting ingredients based on given instructions. Using the ”51k Recipes” dataset, which contains detailed recipe information, we explored and fine-tuned various large language models (LLMs), including GPT-2, T5 (Text-To-Text Transfer Transformer), Gemini, etc, to identify the most effective approach for these tasks. Key challenges addressed include handling large datasets, ensuring the relevance and accuracy of outputs, and optimizing models for bidirectional task processing. Through comprehensive preprocessing and fine-tuning using PyTorch, the chatbot was trained to deliver coherent and contextually appropriate responses. The models were evaluated using metrics such as BLEU scores and human feedback, with notable improvements observed in instruction fluency and ingredient prediction accuracy. This project demonstrates the potential of LLMs in culinary applications and sets the ground- work for creating versatile, user-friendly tools for home cooks, professional chefs, and culinary learners. Future work involves refining dataset quality, exploring larger instruction-tuned models, and integrating the chatbot into practical applications such as voice assistants and cooking platforms.

2024-12-08T00:00:00Z Sethi, Alhad Mukherjee, Manuj (Advisor) http://repository.iiitd.edu.in/xmlui/handle/123456789/2082 2026-09-03T05:55:48Z 2024-11-27T00:00:00Z

Title: Learning from dependent data Authors: Sethi, Alhad; Mukherjee, Manuj (Advisor) Abstract: In this work, we give generalization bounds of statistical learning algorithms trained on samples drawn from a dependent data source both in expectation and with high probability, using the Online-to-Batch conversion paradigm. We show that the generalization error of statistical learners in the dependent data setting is equivalent to the generalization error of statistical learners in the i.i.d. setting up to a term that depends on the decay rate of the underlying mixing stochastic process. Our proof techniques involve defining a new notion of stability of online learning algorithms based on Wasserstein distances and employing “near-martingale” concentration bounds for dependent random variables to arrive at appropriate upper bounds for the generalization error of statistical learners trained on dependent data. Finally, we prove that the Exponential Weighted Averages (EWA) algorithm satisfies our new notion of stability and instantiate our bounds using the EWA algorithm.

2024-11-27T00:00:00Z Gupta, Arsh Makkar, Kshitij Bagler, Ganesh (Advisor) http://repository.iiitd.edu.in/xmlui/handle/123456789/1614 2024-05-24T22:00:26Z 2023-11-29T00:00:00Z

Title: Cuisine fusion Authors: Gupta, Arsh; Makkar, Kshitij; Bagler, Ganesh (Advisor) Abstract: With growing diversity in personal food preference and regional cuisine style, personalized information systems that can transform a recipe into any selected regional cuisine style that a user might prefer would help food companies and professional chefs create new recipes. The aim of the study is to explore computational techniques which can be utilised in order to convert a recipe which belongs to a cuisine (Source cuisine) to another cuisine (Target cuisine) by changing one ingredient from the Original recipe. For ease of understanding we will call the starting recipe from the Source cuisine as Original recipe and the final recipe which belongs to the Target cuisine as the Transformed recipe. There are two major tasks that need to be done in order to change a recipe from one cuisine to another computationally. (1) Swap each ingredient of the Original recipe with the ingredients present in the database and, (2) Classify the recipe based on its ingredients and check which cuisine does the recipe belong to. The Dataset used mainly comprises of labeled corpus of Yummly Dataset recipes. We make use of different Machine Learning, natural Language Processing and Deep Learning techniques to achieve the aim of the study. In recent years, Travel and Tourism has flourished and different ethnicities have started to live in the same countries. Some people feel the need of fusion cuisines. Some people also love to cook their own food and customize the recipes to their need. These types of computational models and studies in the field of Computational Gastronomy are not only research fields, and can also be used to create new recipes and innovation in the food industry.

2023-11-29T00:00:00Z Mishra, Dhruv Bajaj, Kshitij Chatterjee, Bapi (Advisor) http://repository.iiitd.edu.in/xmlui/handle/123456789/1613 2024-05-24T22:00:25Z 2023-11-29T00:00:00Z

Title: Relaxed concurrent counting bloom filters Authors: Mishra, Dhruv; Bajaj, Kshitij; Chatterjee, Bapi (Advisor) Abstract: Counting Bloom filters are highly space-efficient with a small probability of false positives. Concurrent access to a Counting bloom filter can greatly increase its insertion and query throughput.

2023-11-29T00:00:00Z