DeepONet is a neural network architecture designed for operator learning, which involves mapping functions to functions. This approach is particularly effective for problems in infinite-dimensional spaces, such as solving partial differential equations (PDEs) or modeling scientific simulations. This implementation extends the standard DeepONet architecture by adding additional layers after combining the branch and trunk network outputs. Neural operator learning Operator learning uses machine learning to approximate mathematical operators. Unlike traditional machine learning methods that work with finite-dimensional data, operator learning addresses transformations in infinite-dimensional spaces, making it essential for solving PDEs and other function-based tasks....

This scientific project develops an interpretable model for classifying protein sequences into the most common protein families found in the UniProt Knowledgebase. The study employs common NLP techniques and compares various machine learning models, such as k-nearest neighbors, decision trees, and random forests. The comprehensive analysis and detailed implementation can be accessed through the following link: Protein Family Classification Protein Family ClassificationPreview

I wrote this textbook in preparation for the machine learning course exam. It is an overview of key concepts that I personally found important or interesting. For a deeper understanding of the topic, I recommend the following literature: Murphy, Kevin P.: Probabilistic Machine Learning: An Introduction, MIT Press Bishop, Christopher M.: Pattern Recognition and Machine Learning, Springer Goodfellow, Ian; Bengio, Yoshua; Courville, Aaron: Deep Learning, MIT Press Jurafsky, Dan; Martin, James H....

Introduction This analysis explores the impact of arm bone length on the survival of sparrows during winter storms. It uses statistical methods such as distribution function estimation, parameter estimation, simulation, confidence interval calculation, mean value testing, and equality of means testing to investigate the relationship between arm bone length and sparrow survival. The primary objective is to determine whether arm bone length influences sparrow survival during winter storms. Conclusion The dataset used in the analysis consists of arm bone lengths of 59 adult male sparrows, with 24 recorded as deceased and 35 as survivors....

Project BVVIZ is a tool that provides a user-friendly playground for running noisy quantum simulations and visualizing the Bernstein-Vazirani quantum algorithm. source: bernstein-vazirani.streamlit.app The Bernstein-Vazirani protocol is a quantum algorithm introduced in 1992, by computer scientists Ethan Bernstein and Umesh Vazirani. It was shown that there can be advantages in using a quantum computer as a computational tool for more complex problems than the Deutsch-Jozsa problem. It has a potential use in classical cryptography and quantum key distribution and communication....

This project explores deep learning approaches using the Fashion MNIST dataset. The study compares various neural network variants, such as dense and convolutional networks (CNNs), and investigates different regularization techniques, including dropout, batch normalization, L2 regularization, as well as deep and wide architectures. Additionally, it compares the performance of different optimizers. The full analysis can be accessed through the following link: Exploring DL approaches Exploring deep learning approaches with Fashion MNISTFrom Zalando’s article images at github....

Introduction This analysis explores the distribution of GDP among European countries in 2014, measured in euros per capita at market prices. It uses statistical methods such as linear regression and its variants, tests for normality and homogeneity, ANOVA, VIF, and model-submodel testing. The study identifies the most influential indicators that model GDP effectively. Conclusion In conclusion, the analysis highlights that earnings and employment are the most significant indicators in the simplified final submodel....

Project Overseer is a year-long initiative honoring George Orwell and his warning about the dangers of surveillance. Inspired by his book 1984, which describes a world under constant government watch, the project Overseer aims to highlight the threat of surveillance through a thought-provoking artwork. Conceptual design drafts for the enclosure In this project, we create a robot that tracks faces in real-time. To bring this to life, we needed software capable of efficiently planning and controlling the robot’s arm....