Aman | अमन's Projects
This repository hosts all the assignment solutions, assigned to ACM @j23 team members by us.
Here I have done various feature extractions upon audio samples, and this repository also contains all the work I have done in audio analysis. The aim of this repository is to host the methods need in other audio-analysis-projects that I would be doing hence forward.
Awesome-LLM: a curated list of Large Language Model
Hand Written course notes of Deep Learning Specialization by Andrew NG on Coursera
Class notes for CS 131.
This repository hosts all the dissusions I took on Machine Learning/ Deep Learning and Theoritical Computer Science, and their materials / notes that I used for the demonstration during the lecture.
J.P. Morgan Quant Challenge 2022 Questions
This repo contains various data analysis, I have done on various kaggle datasets. To most extent this repository is held for personal uses, but anyone interested might refer it for more insights.
A complete overview and insights into AI-Text detection :seedling: using the powerful BERT(Bi-directional encoder representation transformer) to predict if a text is AI-generated :sunflower: or Human-authored :rocket:
LyricLoom is an API for hit-song-prediction using inception-CNN for low level feature extraction and DNN for music tag generation. When queried it would return the percentile popularity of the song in its genre.
The aim of this project is to foster coding and implementing algorithms from scratch. Here I have implemented various Machine Learning Techniques from scratch and compared how well they perform to pre-exisitng trained models.
I made a Portfolio Optimiser using Hadamard Gate and Quantum circuits. I used a Qiskit simulator (qasm_simulator) to simulate the circuits of qubits. I also compared the quantum approach with classical optimisation techniques & discussed the differences. Monte Carlo Simulation of the assets was also done to forecast their future variations.
The objective of this project is to develop a Monte Carlo simulation model for portfolio optimization to maximise an investor's max returns off a given investment amount vested among various assets. It required to construct and analyze portfolios composed of various asset classes (e.g., stocks, bonds, and alternative investments) to maximize expect
Implemented a LightLGM model :dizzy: capable of predicting the closing price movements for hundreds of NASDAQ listed stocks :seedling: using data from the order book & the closing auction for Optiver's Trading Competition :rocket:
Experimental study on the orientation of _ elongated, oblate spherical, prolate (elongated, cuboidal, cubical) fluidized bed particles _ with the help of OpenCV and Hough Transform
Summaries for exciting works in the field of Deep Learning.
Hydrogen production through photo-bioreactor systems offers a promising pathway for sustainable energy generation, utilizing phototrophic microorganisms to convert wastewater into green hydrogen. Our pipeline aims to design and optimize such a system targeting a production capacity of 0.5-1 kg/day of green hydrogen.
Trained CNN models, to predict the health of the vegetables by analysing the leaf photos of various vegetables like potato, tomato and Bell pepper. Used methods like data augmentation, addition of droupout layers and regularisation. To further increase the accuracy of the predictions ot over 99%.
Courses, Articles and many more which can help beginners or professionals.
Quant prep resources/logs
My quant portfolio leverages quantitative finance and data-driven insights to optimize investment strategies. Using advanced models, statistical analysis, and machine learning, I develop systematic trading strategies to capitalize on market inefficiencies and generate alpha.
usage of RNNs and LSTMs architecture for multivarate as well as univariate modelling of panel data and time series data. It helps in predicting the future trends, by analysing window sections of the historical data.
Developed a sophisticated machine learning model capable of generating diverse interview questions aligned with specific topics, ensuring depth of conversation. Integrated advanced Natural Language Processing (NLP) algorithms to analyse spoken responses, identifying grammatical errors & offering accurate corrections after the interview.