I'm a recent Master's graduate in Physics of Data with a strong passion for data science, machine learning, and data analysis. My academic and project experience spans diverse fields, from astrophysics to molecular dynamics and epidemiology, showcasing the versatility of data-driven approaches in solving complex problems.

• 🌐 Data Science and Analysis
  Proficient in Python, R, and SQL, with extensive experience in data manipulation and big data processing using tools like Pandas, PySpark, and NumPy.

• 🔍 Machine Learning
  Specialize in neural networks and computer vision, leveraging frameworks like PyTorch and Scikit-learn. I've also worked on advanced methods for dimensionality reduction and probabilistic models.

• 🧬 Data Analysis for Scientific Research
  Applied statistical mechanics, Bayesian inference, and advanced simulation techniques to analyze stem cell dynamics, molecular dynamics, and epidemiological models.

Tools: Git, Jupyter, Spark, Kafka, Docker

Explored 3D object classification using Variational Autoencoders (VAE) integrated with PointNet, a neural network model designed for point cloud data.

Developed a multi-strain epidemiological model to study influenza dynamics, employing numerical simulations to understand the impact of cross-immunity and strain interactions.

Developed a real-time dashboard to analyze cosmic ray data using Apache Spark and Kafka. Demonstrates expertise in big data streaming, pipeline architecture, and interactive data visualization.

Utilized Markov State Model analysis for molecular dynamics simulations of LB6 peptidomimetics. Incorporated PyEMMA and MDAnalysis to model and interpret complex molecular behavior.

Collaborated on a project using Infomap to analyze pollination networks, highlighting the ecological impact of pollinators in forest systems.

Applied Bayesian methods to analyze real-world vaccine efficacy data, providing probabilistic insights into the effectiveness of COVID-19 vaccines.

Analyzed muon data from particle detectors, showcasing skills in high-energy physics data processing and signal extraction techniques.

Studied X-ray binary systems with a focus on low-mass counterparts, applying statistical tools to astrophysical datasets.

• Programming: Python, R, SQL
• Data Processing: Pandas, NumPy, PySpark
• Machine Learning: Scikit-learn, PyTorch
• Visualization: Matplotlib, Seaborn
• Big Data: Spark, Kafka
• Scientific Computing: PyEMMA, MDAnalysis, Biopython

• LinkedIn: Mariam Hergnyan
• GitHub: Mariam Hergnyan
• Email: [email protected]