Avikshit Banerjee's Projects
AI Transcription using AssemblyAI
Use this template if you need a quick developer / data science portfolio! Based on a Minimal Jekyll theme for GitHub Pages.
A collaborative filtering-based book recommendation system with a user-friendly Flask-based web interface
A retrieval-based chatbot using deep learning for giving appropriate responses to user inputs. It is widely used in the industry to make goal-oriented chatbots where we can customize the tone and flow of the chatbot to drive our customers with the best experience.
Code for a gesture based door locking mechanism using ATMEGA 18 microcontroller and radio tranceivers
Specify what you want it to build, the AI asks for clarification, and then builds it.
GPT 3.5 powered chatbot which can be trained on a local knowledgebase
This is a basic Data Science Hackathon Machine Learning Pipeline built using Ensemble and Stacking Methods in Python
A basic CNN is deployed to classify pictures of cats and dogs
Notebooks for the Practicals at the Deep Learning Indaba 2022.
For experimental purposes
Created an app using Langchain, Streamlit and FAISS which uses OpenAI API to use GPT to answer questions from uploaded PDF files.
This repository contains everything you need to become proficient in ML/AI Research and Research Papers
This repository contains the source code for an app that generates summaries for text documents. Tools: Fast API, Docker, AWS.
Seamlessly integrate powerful language models like ChatGPT into scikit-learn for enhanced text analysis tasks.
Semantic, Sentiment and Geographical Analysis of low-frequency linguists on Twitter
This is a repository containing the links to my Tableau projects
A GPT 3.5 based chatbot that can generate responses in the style of Rabindranath Tagore, providing an immersive experience for users who interact with it.
An end to end implementation of an LLM-based text summarisation app
This repo contains the code for predicting the energy usage a year into the future using 16 years of time series usage data, using XGBoost and ARIMA
Credit Scoring and Loan Approval Prediction: Utilizing a Stacking Classifier with Feature Engineering, PCA, and Hyperparameter Tuning for accurate loan approval predictions. Includes extensive data preprocessing and model evaluation.
Visual EDA of Uber ride data