Nijat Zeynalov's Projects
Federated Learning for News Categorization in Azerbaijani
This model is a fine-tuned version of facebook/mms-1b-all on the common_voice_15_0 dataset.
Estimating real-world fuel consumption of vehicles using the multiple machine learning methods
Generate images of clothing items by using Deep Convolutional Generative Adversarial Networks (DCGANs)
An imbalanced classification problem is a problem that involves predicting a class label where the distribution of class labels in the training dataset is not equal.
This project allows you to convert image into Azerbaijani handwriting
Sentiment Analysis using Recurrent Neural Network on 50,000 Movie Reviews Compiled from the IMDB Dataset
This project implements a sentiment analysis pipeline for Azerbaijani language using the BERT model, facilitated by the Kedro framework.
In this project, I have built a regression model using the deep learning Keras library, and then I have experiment with increasing the number of training epochs and changing number of hidden layers and you will see how changing these parameters impacts the performance of the model.
This repository consist of codes which I have mentioned my tutorial articles on medium
This project is a Streamlit app that uses the mGPT-XL (1.3B) model to generate Azerbaijani text. Users can input partial text, and the model will complete it with contextually relevant text in Azerbaijani.
In this notebook, I have done big data processing, analysis and ML with PySpark. Firstly, I have explored and preprocessed the dataset that I loaded in at the first step the help of DataFrames.
In this notebook, I will make my first neural network(ANN) using keras framework. The data is about mobile phones of various companies and consist of features of a mobile phone(eg:- RAM,Internal Memory etc) and its selling price.
mT5-small based Azerbaijani News Summarization
Developing a Neural Machine Translation Model (Azerbaijani - English)
New product demand forecasting via Content based learning for multi-branch stores: Ali and Nino Use Case
The purpose of this project is to prepare a spell checker for Azerbaijani language by implementing a Azerbaijani corpus to Norvigβs algorithm. The corpus I created consists of 1478667 words collected from 47 books in 6 fields (biology, geography, detective, literature, encyclopedia, novel)
Opening a New Restaurant in Baku, Azerbaijan
Optuna is an open-source hyperparameter optimization framework to automate hyperparameter search. The key features of Optuna include automated search for optimal hyperparameters, efficiently search large spaces and prune unpromising trials for faster results, and parallelize hyperparameter searches over multiple threads or processes.
Image classification using Convolutional Neural Networks (ConvNets). The model predicts whether the inserted image is a photo or a painting.
My portfolio website with built-in blogs and courses support
Predicting Bike Rental Usage by using Artificial Neural Networks (Regression task)
Predicting House price using Artificial Neural Networks
In this game, I have used pygame which is a cross-platform set of Python modules designed for writing video games. Then, I have applied Deep Q-learning. We have two enemies in the game and one player trying to avoid these enemies.
In this project, I developed a Pix2Pix generative adversarial network for image-to-image translation. I have used the so-called maps dataset used in the Pix2Pix paper.
Scikit Optimize implements several methods for sequential model-based optimization. The library is very easy to use and provides a general toolkit for Bayesian optimization that can be used for hyperparameter tuning. It also provides support for tuning the hyperparameters of machine learning algorithms offered by the scikit-learn library.
Scraper chatbot which answer more than a half bilion questions.
In this notebook, I have used scraping method for movies in the "Rotten Tomatoes" website. This project based on "Web Scraping and API Fundamentals in Python" course of 365 Data Science.
I have implemented Multi Layer Perceptron model to learn and predict the sentiment of sentence written in Azerbaijani. In order to perform this sentiment task, we use a mixture of baseline machine learning models and deep learning models to learn and predict the sentiment of binary reviews.