Koray's repositories
Aphasia-portfolio
Data Science: Speech-to-Phoneme
news-article-vector-search
Blazing fast real-time NRC search empowered with multilingual LLM and Qdrant
mlops-mlflow-minio
MLOPS with MLFLOW, MinIO (S3), MySQL and Docker
dcnn-from-scratch
Deep Convolutional Neural Network from scratch. Just NumPy.
nrcnewsapi
NRC = dutch news website. A simple NRC Scraper API written in GO with Colly (scraping framework) and Gin (web framework). This API can be used for building NRC-news web or mobile app (https://github.com/ciCciC/nrcnewsapp)
nrcnewsapp
A simple NRC Android app which makes use of the NRC Scraper API (https://github.com/ciCciC/nrcnewsapi) for populating the front end.
anomalyAENN
An anomaly detection system (ADS) using Dense AutoEncoder Neural Net developed with Tensorflow and hosted within the framework of Streamlit. ADS has integrated default data sets that can be utilized for analysis and training purposes.
callflow-visualizer
A web component which gives the possibility to visualize the structure of a CallFlow in an interactive network graph.
dataMiningNN
Cultural analytics concerns the use of data and digital methods for the inquiry of (large) cultural corpora. Using text mining and statistical analysis with Python, exploratory programming and digital methods, will employ data mining techniques on text, image or video archives. The objective is to develop insights into patterns of cultural production and media formats.
ImageCompressorProject
AI-powered compression as latent space representations
MasterThesisPartialRDFschemaRetrieval
Master Thesis: Partial RDF Schema Retrieval
network_science
Network Science
dsbiasnessgendertvshow
Analyzing biasness towards (fe)male within TV show discussions by utilizing NLP and Word2Vec
dsclassifyingmusicgenre
Classifying certain music genre and others utilizing Log-likelihood Ratio and Logistic Regression
dscnnandfoxnews
Analyzing the topics that are prominent in the distribution of tweets from CNN and FOXNEWS by utilizing NLP and LDA mallet model (Latent Dirichlet Allocation)
dsemotionmovietrailers
Analyzing the occurrence of emotions within movie trailers over time utilizing Object, Face and Emotion detection models
embedding-opt
Application of Matryoshka Representation Learning on LLM Embeddings
forecastingUsingDNNets
Time series forecasting energy consumption using Deep Neural Net models
k-medoids-clustering
2021, K-Medoids clustering from scratch
RecommendationSysTopicModel
TV-content Recommendation System using Topic Model for content-based filtering and AI-powered search along with custom algorithms. Additionally, simulation of user behavior.
text-2-image
Text-2-image consisting of min-dalle and Real-ESRGAN
usefulDump
Useful dump