Nijat Zeynalov's Projects
Developing, evaluating and monitoring popular XGBoost model.
HalvingGridSearch, HalvingRandomSearch, Bayesian Optimization, Keras Tuner, Hyperband optimization
The objective of this project is to discover insights into consumer reviews.
In this notebook I’ll use the HMP dataset and perform some basic operations using Apache SparkML Pipeline component. This dataset is a public collection of labelled accelerometer data recordings to be used for the creation and validation of acceleration models of human motion primitives.
Scraping Azerbaijani real estate website and sending whatsapp message with AWS Lambda function that automatically triggered by Amazon CloudWatch.
azcorpus - The largest NLP corpus for Azerbaijani (1.9M documents, ~ 18M sentences)
The aim of this project is to generate fake news in the Azerbaijani language using LSTM Recurrent Neural Networks. LSTM Recurrent Neural Networks are powerful Deep Learning models which are used for learning sequenced data. Here a LSTM model was trained on 65 thousand samples, and it should be able to generate text.
Azerbaijani Medical Forum Question Classification
Azerbaijani News Summary Dataset
AzVoiceSent is research project focused on sentiment classification from voice transcriptions in Azerbaijani. The project has the potential to provide valuable insights into the sentiment expressed by speakers in various domains and applications.
Multi-classificatiion of boats using CNN
Predict whether the cancer is benign or malignant by using KNN
I have built simple versions of some Neural Network architectures (Alexnet, Inception-v1, Resnet-18, Vgg-16) from scratch by using TensorFlow.
OpenAI's CartPole-v1 environment.
Classifying Diabetes using Artificial Neural Networks
Classify traffic signs using CNN
Cleaning Text Manually and with NLTK.
In the project, I have detected concept drift by using adversarial validation and Kolmogorov-Smirnov test which can also be used in the deployed system.
The paper mainly describes the implementation of the Multilayer Perceptron (MLP) model - that can be used to detect sentiments from the text.
I have used Object Detection API and retrain RetinaNet model to spot weapon objects using just 4 training images.
This telegram bot will find easy recipes in Azerbaijani using ingredients you already have in the kitchen.
Ensemble models in machine learning combine the decisions from multiple models to improve the overall performance
Automate your classic machine learning experiments with experimenteer.
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