Music generation using a Long Short-Term Memory (LSTM) neural network. The gennhausser project uses TensorFlow and music21 libraries to create a synthetic dataset, train an LSTM model, and generate music sequences.

Using Deep Learning to Categorize Music through Spectrogram Analysis

LSTM and all other supporting modules are used to predict the next word based on the previous five words.

Many-to-one LSTM neural network for binary sentiment classification of IMDB movie reviews. Built with TensorFlow/Keras as part of Deep Learning coursework. Includes data preprocessing, model training, evaluation, and visualization.

📈 Experimenting with possible closing price predicition using automated systems

Data transform utility for time series

🌾 Bazarya is a lightweight Flask-based web app that uses time-series forecasting to predict daily market prices of essential goods in Ethiopia. Built for low-resource environments to empower farmers, traders, and households with data-driven insights.

Exploration of different models that generate text by predicting the next character.

Tools and templates for organizing research and experiment workflows.