Built a image classification model that classifies images into one of the 43 classes from the German Traffic sign dataset.

XSS Attack Machine Learning detection

This repository contains the implementation of a recurrent neural network (LSTM from keras library) with the purpose of forecasting target time series, given the targets historical records and covariates. The project uses a toy data set, while focusing on the data transformation tasks (pandas dataframes to 3D numpy arrays required by recurrent n…

📈 Forecast weekly and monthly book sales using advanced models like SARIMA, XGBoost, LSTM, and hybrid approaches for accurate retail insights.

A configurable Python framework for comparing time series forecasting models (SARIMA, Prophet, RNN, LSTM) with evaluation & visualization.

binary classifier that utilizes advanced machine learning algorithms and neural networks to accurately predict the success rate of funding applicants

Personal GitHub to host and shares my academic mini-projects related to my master degree.

This is an end-to-end animal face classification model with Keras, KerasTuner, Mlflow, SQLite, Streamlit, and FastAPI which can classify animal faces as either cat, dog or wildlife

This project uses two neural networks to predict Bitcoin's direction of movement (up, down, flat) based on technical indicators calculated using OHLCV data from Bybit (spot trading, 30-minute candles). Technologies: Python, TensorFlow/Keras, NumPy, Pandas, Matplotlib, Scikit-learn,Technical Analysis (ta), requests, keras_tuner

Deep learning powered 100 class image classifier optimized using Keras Tuner for hyperparameter search. Demonstrates training, tuning, and overfitting analysis.

Detecting Pneumonia with Convolutional Neural Networks

The case study is about India's Largest Marketplace for Intra-City Logistics. This dataset has the required data to train a regression model that will do the delivery time estimation, based on all those features.

Portfolio of Deep Learning projects

Google SVHN Prediction using Keras Tuned CNN model and Transfer Learning

End to End implementation for a Flask App in Google Kubernetes Engine. The Notebook has EDA, model selection and training for a unclean structured text data. DNN and Combination of PCA and RandomForest is used for classification.

DeepNet tuned with Kerastuner added with ensemble of LGBM, HistGBM

This repository contains simple usage examples for basic machine learning libraries. These notebooks are tested in Colab.