Page Not Found
Page not found. Your pixels are in another canvas.
Sitemap
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.
Pages
Page not in menu
This is a page not in th emain menu
Posts
How Generative AI and Neuroscience are changing the way we understand intelligence?
Posted:
In the ever-changing landscape of artificial intelligence, two revolutionary fields—Generative AI and Neuroscience—are colliding to transform our understanding of intelligence. This synergistic interaction between robots and the human brain has enormous promise, opening up new horizons in creativity, problem-solving, and the very essence of what it means to be clever. This blog digs at the convergence of Generative AI and Neuroscience and how this collaboration is changing our perspective on intelligence.
Essence of Prompt Engineering with the rise of Large Language Models
Posted:
Creating large language models like GPT-3 and other recent developments in AI have made prompt engineering a popular topic. These models, which contain an incredible amount of parameters and are capable of producing text that is cohesive and contextually appropriate, are immensely flexible tools for a wide range of applications.
Alchemy of Stable Diffusion
Posted:
The creative expressions of humanity have always been reflected in art, in all of its forms. Art has changed, pushed limits, and confounded expectations throughout the ages. The world of art is undergoing yet another seismic transition in the digital era, and the groundbreaking idea of Stable Diffusion lies at the centre of this change.
Finding a balance in Ethical AI between Transparency and Privacy
Posted:
In today’s world, artificial intelligence (AI) has rapidly penetrated various aspects of our lives, making it an essential technology in areas such as finance, insurance, education, retail, and manufacturing. Concerns about privacy, accountability, transparency, and the possibility of bias all figured prominently in this discourse. The key question remains: Should AI be regulated, and if so, how do we carefully strike the delicate balance between regulation and innovation?
experience
Undergraduate ML Researcher at IIT Jodhpur
Research Internship | Remote | Ongoing
- Project: Healthcare Analytics using GANs
- Developing an algorithm for robust classification of chewing moments.
- Working on utilizing flexibility offered by Liquid Neural Networks
- Tech stack: Liquid Neural Network, Machine Learning, Deep Learning
MITACS Globalink Research Internship At University of Calgary
Research Internship | Calgary, Canada | May 2023 - August 2023
- Project: Return on Investment (ROI) of Data Analytics
- Used NLP, Active Learning and requirements dependency extraction to construct a full framework to estimate ROI
- Hosted the application on AWS EC2 and implemented CodePipeline to automate the deployment procedure
- Business Impact: Highlighted possible ROI under several circumstances, potentially helping the business to manage resources and prioritise data-driven plans.
- Tech stack: Deep Learning, Machine Learning, Data Science, NLP, Cloud Computing (AWS), React JS, Flask
Amazon ML Summer School’22
Amazon | Apprenticeship | July 2022
- Competed with the engineering students in India in programming skills, logical reasoning, mathematics and machine learning assessments and was selected among the top few students for this training session
- Hands-on: Deep Neural Networks, Sequential Models, Unsupervised Learning, Causal Inference & Reinforcement Learnin
AutomationEdge, India
Machine Learning Internship | India | June 2022 - July 2022
- Employed Curriculum Learning to progressively present training samples for effective learning.
- Enhanced comprehension of textual customer complaints by implementing NER and POS tagging methods
- Impact: Improved text analytics and Intent Recognition Algorithms
- Tech stack: Machine Learning, Deep learning, NLP, Spacy, Textacy
AutomationEdge, India
Data Science Internship | India | Dec 2021 - Jan 2022
- Formulated predictive models for IT ticket volumes using Deep Neural Networks and worked on Resource Allocation.
- Leveraged NLP techniques to enhance the functionality of ChatBots built with BOT Framework Composer integrating knowledge base with Microsoft Azure.
- Impact: Automation strategies established the groundwork for customer service operations innovation.
- Tech stack: Machine Learning, Deep Learning, Power BI, Microsoft Azure, Bot Composer Framework
projects
Liquid Neural Networks for Enhanced Decision-Making
A decision-making algorithm based on Federated Co-Learning : Bachelor’s Thesis [Ongoing]
- Developing an algorithm to incorporate Co-Training into Federated Learning such that data is decentralized yet benefiting both models mutually.
- Utilizing Liquid Neural Networks as the base model in Federated Learning Network.
Machine Unlearning in Large Language Models using a Neuroscientific Cognitive Approach
Optimizing Unlearning LLMs with advanced neuro-inspired algorithms
- Developed and improved a state-of-the-art unlearning algorithm for Large Language Models by adding extensive representations of the memory system, modulations of the attention mechanism, and other cognitive processes motivated by neuroscience.
- Created an adaptive threshold mechanism for the reconsolidation window to optimise unlearning timing and requirement depending on error severity, concept usage frequency, and emotional connotations.
Q&A: System Based on Google Palm LLM and Langchain
LLM-powered Q&A system using Langchain + Google Palm
- Developed an LLM-powered Q&A system (Langchain + Google Palm) within Streamlit UI to reduce workload for e-learning company.
- Spearheaded the implementation of FAISS vector database for fast retrieval of relevant answers, optimizing system performance and user satisfaction.
- This innovative approach enables real-time response and seamless access to knowledge within the e-learning platform.
Bayesian Meta-Learning
Framework for adaptive learning in constrained data
- Used Bayesian Meta-Learning to design a framework that adapts fast and performs efficiently with limited data.
- Designed a Few-Shot Learning paradigm which achieved 80% accuracy in the classification tasks.
Meta Learning with GANs for Text Classification
ML framework for Text Classification using Meta-Learning with GANs
- Applied a cutting-edge Meta-Learning framework to substantially improve model performance and facilitate rapid adaptation to dynamically changing environments and tasks.
- Developed GAN for data augmentation consisting of a multi-layered generator and discriminator.address Catastrophic Forgetting during Meta-Learning.
- Achieved an accuracy of 95%, compared to 87% for baseline models.
Bias Detection in Federated Learning and Swarm Learning
Technique to detect biases in Distributed ML Algorithms
- Designed 5 clients and 5 agents system for distributed learning.
- Explored Differential Privacy techniques to add noise to the aggregated model updates, ensuring privacy in Federated Learning.
- Analyzed security in Swarm Learning using Decentralized Identity Management.
AI For Healthcare
Framework for harnessing ML to create Wearable Medical Technology
- Carried out clinical studies with the goal of categorising mandibular motions during eating.
- Real-time sensor data acquisition and transmission enabled by the HC-05 Bluetooth Module.
- Compared computational efficiencies of LNN and LSTM for sequential data.
Vehicle Detection Through Transfer Learning
A Transfer Learning framework for detecting vehicles in aerial images
- Utilised the potential of transfer learning with VGG16 network architecture.
- Attained quicker convergence on vehicle detection dataset.
- Conduced trials on grey and coloured images and obtained model accuracy of 60%.
research
Enlightening Hope: AI-Driven Empowerment of Unorganized Labor in Developing Nations
International Journal Of Research And Analytical Reviews - Issue 3, Volume 10 2023
The idea of this project was centred on the use of federated learning and the upholding of data privacy in AI driven systems.
View here
Incorporating Deep Q - Network with Multiclass Classification Algorithms
IJCRT Issue 11, Volume 8 2023
In this study, we investigate the potential of Deep Q-Network (DQN) to enhance multiclass classification algorithms, with a specific focus on predicting financial distress in companies and broader applications in fields such as finance and risk management. Key algorithm used - Reinforcement Learning.
View here
AIOptimizer - A Reinforcement Learning-based software performance optimisation prototype for cost minimisation
Submitted: IEEE - International Conference on Innovations and Challenges in Emerging Technologies 2024 [under review] 2024
This paper is about the development AIOptimizer, a cost-reduction software performance tool, with a reinforcement learning-based recommendation system.
View here