LearnAnalyzeResearch
I am Kushagra Agrawal, a dynamic and dedicated Computer Engineering student with a passion for catalyzing research organizations through innovative problem-solving and practical implementation.
I specialize in Machine Learning, Deep Learning, Transformers, and Artificial Intelligence. I am committed to giving back to society with the skills I learn.
Research
Actively contributing to the scientific community as a researcher and reviewer through research and reviewing articles, book chapters, and magazines
Learn
An active learner in the field of Machine Learning, Deep Learning, Transformers, Vision Transformers, LLMs and Cloud Services
Public speaking
I love to share my knowledge and experience with the community. I speak at conferences and meetups, and I am always open to new opportunities.
Projects
I love taking the lead on projects and have successfully spearheaded several initiatives. Below are some of the projects I have led:
Medicinal Leaf Detection CNN Model
PhytoPixel is an innovative solution addressing the critical challenge of identifying medicinal plants and raw materials in Ayurvedic Pharmaceutics. Leveraging a sophisticated Convolutional Neural Network (CNN) model, it ensures precise plant identification, thus preserving the authenticity of Ayurvedic medicines. This technology not only eliminates the risks of misidentification and adulteration but also fosters consumer trust and promotes sustainable practices. The solution's adaptability allows it to cater to diverse plant species across different regions, making it a valuable tool for wholesalers, distributors, and healthcare professionals. Ultimately, PhytoPixel bridges the gap between traditional wisdom and modern technology, enhancing the efficacy and integrity of Ayurvedic medicine.
Introduction to GenAI and Simple LLM Inference on CPU and Fine-tuning of LLM Model to Create a Custom Chatbot
This project focuses on developing and optimizing the Dolly-v2-3b Large Language Model (LLM) for creative text generation. Trained on a specialized dataset of 15,000 instruction/response pairs, the 3 billion parameter model excels in generating engaging narratives. Integration with Intel Extension for Transformers enhances performance, optimizing hardware use for faster inference. Evaluation metrics like eval_loss and eval_ppl confirm its accuracy and context-sensitivity. Benchmarks show low latency and high throughput, processing 100 samples in 14.16 seconds at 7.061 samples per second. Ethical fine-tuning promotes unbiased storytelling, ensuring socially conscious outputs
Publications
I am an active contibutor to the scientific community. I write articles, conference papers, journal papers, book chapters and much more. I am open to collaboration. Have a look at my latest publications below.
Artificial Intelligence Innovations: Inception of new horizons in food processing sector
- #Conference Paper
- #SILCON - 2023
- #IEEE
Deep Learning in Industry 4.0: Transforming Manufacturing Through Data-Driven Innovation.
- #Conference Paper
- #ICDCIT - 2024
- #Springer
Revolutionizing Brain Tumor Detection: The CNN-Based Medical Imaging Breakthrough
- #Magazine Article
- #OR/MS Today
- #INFORMS
AI/ML Applications in Agriculture and Food Processing
- #Upcoming
- #Book Chapter
- #Food Industry
- #Agriculture
Recent Events
I love to take time off from my daily schedule to connect with people in different workshops, summer schools, conferences and much more.
Participation in ICTMS – 2024 at KIIT Deemed to be University
- International Conference on Thermofluids and Manufacturing Science 2024•
- KIIT Deemed to be University •
- 2024-07-09
I am thrilled to share that I participated in the ICTMS – 2024 held at KIIT Deemed to be University. This international conference provided a platform for researchers, scientists, and engineers to discuss pioneering research in the field of Thermofluids and Manufacturing Science.
Machine Learning for Biomedical Signal Processing Course at ABV-IIITM
- Machine Learning for Biomedical Signal Processing Course•
- ABV-Indian Institute of Information Technology and Management •
- 2024-06-30
I am thrilled to share that I recently completed a short-term, hands-on course in Machine Learning for Biomedical Signal Processing from ABV-Indian Institute of Information Technology and Management. This course enabled me to learn advanced techniques and practical applications of machine learning in the field of biomedical signal processing.
International Conference of Distributed Computing & Intellignet Technologies
- International Conference of Distributed Computing & Intellignet Technologies•
- KIIT Deemed to be University •
- 20-01-2024
I attended ICDCIT - 2024 as a presenting author. I had presented my paper on "Deep Learning in Industry 4.0: Transforming Manufacturing Through Data-Driven Innovation", it was an invaluable experience to be with some of the greatest mind.
8th CVIT - Summer School on AI organised by IIIT Hyderabad
- CVIT Summer School on AI•
- IIIT Hyderabad •
- 07-07-2024
Attending the CVIT - Summer School on AI 2024 at International Institute of Information Technology Hyderabad (IIITH) was an enriching and unforgettable journey! This experience was more than just acquiring knowledge; it was about the invaluable lessons learned, the meaningful connections made, and the lasting friendships formed.