Maze Applied Reinforcement Learning Framework

Live-Transcription (STT) with Whisper PoC

Applied machine learning toolkit implementing Double Machine Learning for Energy Analytics.

Deep Learning papers reading roadmap for anyone who are eager to learn this amazing tech!

Small library to help resolve k-armed bandit problems

Machine Learning and Deep Learning in Bioinformatics - Master's thesis repository

Automated the process of training time-series data with multiple Machine Learning and Stats Models to output the most accurate forecast result

State-Of-The-Art Transformer Models

Comparative analysis of sentence embedding models as low-cost proxies for Google LaBSE in Semantic SEO, AI Search, content relevance, link relevance and topical authority scoring. The coding stack for the analysis is stored here.

Multi-task CNN for real-estate images: room type classification and photo quality estimation with PyTorch, failure analysis, and Streamlit demo.

This project contains the code to perform a task of Particle identification (PID) in Astrophysics, comparing Deep Learning and Classical Machine Learning approaches. Data are provided by Agile team (http://agile.rm.iasf.cnr.it/) and the goal of the analysis is to provide a Statistical model which is able to distinguish gamma-ray photon for backg…

Engineering-first data validation and structuring baselines for integrity and RBI decision support.

Xandly5 is a lyrics generator powered by Natural Language Processing using the Keras and TensorFlow frameworks.

Intelligent System Applications (ISA_I) Foundations of Generative AI and Applied Machine Learning @ FIIT STU in Bratislava

Hybrid AI System For Microbiology Phenotype Identification

[2021 Summer Research in Applied Machine Learning] Built two desktop apps using PyQt5 to perform pixel-classification with k-means clustering to explore the chemical composition of objects scanned with high-resolution x-rays.

Work has been done on COVID-19 Bangladesh situation .Where Data Analysis, Data Visualization, Supervised Learning and Unsupervised Learning are used.

NLP: Performing sentiment analysis on text-tweet data from Twitter.

A crawler that transforms unstructured web data into a corpus that can be analyzed and searched semantically.

ACAML is an Adaptive Constraint-Aware AutoML web app built with Streamlit. It automatically selects the best model for regression or classification tasks using FLAML, displays performance metrics, and provides SHAP-based feature explanations. Empower users to run and interpret ML models easily.