roupenminassian Goto Github PK

14-go-live

applied-machine-learning-explainability-techniques

Applied Machine Learning Explainability Techniques, published by Packt

behrt

Code for BEHRT: Transformer for Electronic Health Records

crc-p

This project explores the classification of human activities using wearable sensor data, investigating different modeling approaches, feature extraction methods, and evaluation metrics to optimize real-world applications.

cv

Print-friendly, minimalist CV page

esm

Evolutionary Scale Modeling (esm): Pretrained language models for proteins

freelance

For freelance projects, can also include code to Kaggle competitions

hemorrhage-detection

This repository contains our implementation and training of a combined recurrent-convolutional DNN for intracranial hemorrhage (bleeding inside the brain) detection on CT scans.

hub

where we'll put all of our things

idtxl

The Information Dynamics Toolkit xl (IDTxl) is a comprehensive software package for efficient inference of networks and their node dynamics from multivariate time series data using information theory.

keras-ncp

Code repository of the paper Neural circuit policies enabling auditable autonomy published in Nature Machine Intelligence

liquid_time_constant_networks

Code Repository for Liquid Time-Constant Networks (LTCs)

llmxtwitter

This project leverages advanced machine learning techniques to analyse Twitter activity during the 2020 Nagorno-Karabakh conflict. By diving deep into the digital narratives, we aim to understand the role of social media in shaping public opinion and disseminating information (or misinformation) in times of geopolitical crises.

mtsne

Multivariate time-series t-Distributed Stochastic Neighbor Embedding

openai-python

poogle-search

ppscore

Predictive Power Score (PPS) in Python

protein_bert

roupenminassian

Config files for my GitHub profile.

semantic-search-with-sbert

Build Semantic Search with S-BERT and Fine-tune your model in unsupervised way

streamlit-example

Example Streamlit app that you can fork to test out share.streamlit.io

timeseriesforecastinginpython

traffic-analysisxbuiltenvironment

Harness the power of computer vision to analyze traffic from video footage. This tool identifies vehicles, gauges their speeds, and categorizes them by lane using a bird's-eye view transformation. Integrated with Hugging Face's pretrained models, it offers precise vehicle detection, serving as a vital tool for traffic management and research.

transformer_notebooks

Jupyter notebooks for the Natural Language Processing with Transformers book

uts-dsi-x-disability-research-network

This repository contains work conducted with the Data Science Institute and Disability Research Network at the University of Technology, Sydney.

uts-hass-dsi