Hi, my name is
HANS HEJE
I'm a data enthusiast; cryptology lover; machine learning nerd. Currently working as an student software engineer at IBM
01. About me
Dane currently residing in the capital region of Denmark. My passion is anything data related: Visualizing, extrapolating, and securing data. My primary technological competencies lie in the following areas: Software architecture, cyber security, software development using principles of OOP (Java, C#, and Python), full stack development (MERN stack, SQL), digital electronics (C), quantum computing (Qiskit) and general data science including but not limited to deep learning, computer vision and natural language processing. All of which I have applied either through work or in large solo- or group projects consisting of 6-7 people.
Professional experience 02. Where I have worked
Software Engineer @ IBM
February 2022 - Present
Technical student assistant at the firm IBM. Handled rapid prototyping and pinpointed customer requirements. Developed experimental and proof of concept systems leveraging 'AI', machine learning and hybrid cloud architecture. Developed and optimized a machine learning model to predict sales of various items at different locations for Smukfest, including the implementation of cloud-based pipelines for improved efficiency. Processed massive live data streams through peak analysis to filter and retain critical components of time series data, reducing the size of incoming data for wind turbine testing in the ReliaBlade project at DTU. Developed a cloud-based application that utilized machine learning for data analysis and real-time game phase estimation using computer vision, in collaboration with DBU. This effort contributed to the Danish national football team’s success in tournaments, increasing their FIFA ranking from 16 to 11. Demonstrated use cases, and developed visualization tools, of quantum algorithms in the Qiskit eco system.
03. Education
2023-2025
Technical University of Denmark
MSc. Computer Science and Engineering
Studyline: Algorithms and Artificial Intelligence
Focus Area: Machine Learning
2020-2023
2016-2019
Albertslund Gymnasium
Math, Biotech., Robot-tech. and Chemistry A-levels.
04. Publications
CreoleVal: Multilingual Multitask Benchmarks for Creoles
2023 • Computation and Language, arXiv
Creoles represent an under-explored and marginalized group of languages, with few available resources for NLP research. While the genealogical ties between Creoles and other highly-resourced languages imply a significant potential for transfer learning, this potential is hampered due to this lack of annotated data. In this work we present CreoleVal, a collection of benchmark datasets spanning 8 different NLP tasks, covering up to 28 Creole languages; it is an aggregate of brand new development datasets for machine comprehension, relation classification, and machine translation for Creoles, in addition to a practical gateway to a handful of preexisting benchmarks. For each benchmark, we conduct baseline experiments in a zero-shot setting in order to further ascertain the capabilities and limitations of transfer learning for Creoles. Ultimately, the goal of CreoleVal is to empower research on Creoles in NLP and computational linguistics. We hope this resource will contribute to technological inclusion for Creole language users around the globe.
Lent, H., et al. "CreoleVal: Multilingual Multitask Benchmarks for Creoles." arXiv:2310.19567 [cs.CL], 2023.05. Highlighted Projects
Reducing Carbon Footprint of Electricity
2021 • JavaScript, MongoDB, Node.js
We analysed a problem and created requirements through a detailed 80-page rapport. From this we deduced that we could cut around 4% of the global carbon footprint if people used electricity when it was more sustainable. From this we created a dynamic website that through a API got current energy data live and displayed it using graphs. Using a SARIMA model we tried to forecast when throughout the day was the best time to use electricity. Using the model’s information, we made a custom recommendation system that gave individual recommendation based upon when was the cleanest time to use electricity.
Github•Showcase06. Courses and Certificates
Cryptography Course @ Stanford Online
November 2021 • Grade: 92%
Learned classic cryptography, DES and AES, the RSA system, digital signatures, secret sharing, the discrete logarithm problem, and its use cases. Learned different types of symmetric and asymmetric cryptography, including the math behind it and the different types of attacks against them, such as but not limited to: Chosen plaintext attack (CPA), Chosen Ciphertext Attack (CCA), Birthday attack and existential forgery. Learned about key principles, such as semantic security, perfect secrecy, and integrity (Message Authentication Code).
