Artificial Intelligence

Create advertising campaigns at the touch of a button

Introduction In the digital world, an online presence is essential for companies. But effective marketing can quickly become expensive, especially when experienced professionals are needed. Even experienced marketers need time to design a campaign. As artificial intelligence is increasingly being used for precisely such time and money-intensive tasks, we wanted

Summarizing Forum Threads Using Large Language Models

This project was a part of a master's degree lecture on Deep Learning in computer science at the Kaiserslautern University of Applied Sciences. It was conducted under the supervision of Professor Dr. Bastian Beggel. Internet community platforms, especially discussion forums on specialized topics with a knowledgeable community, quickly grow to

Tell-HS-KL (RAG): How AI can explain your university?

Students and applicants need a wide range of information to find their way around in university life. What are the requirements for my study? Which person do I need to address for my internship? Which study programme suits me? The first source of information is a university’s website. But

Use of LLMs as a Socratic teacher in the context of database teaching

The DBCoach (https://dbcoach.hs-kl.de/) is an interactive eLearning program at Kaiserslautern University of Applied Sciences that is designed to help users learn SQL and Java. As part of the course "Deep Learning", it was evaluated whether and how Large Language Models (LLM) can be connected to

AI infrastructure at a modern applied university: a look behind the scenes

The topic of artificial intelligence (AI) has become increasingly important and relevant in recent years. The majority of the population now consciously uses AI systems in their everyday life, such as the chatbot system ChatGPT or voice assistants like Siri and Alexa. However, we are also increasingly interacting unconsciously with

Mastering Othello: Unleashing the Power of Double Deep Q-Learning

Our Motivation Why did we choose Q-Learning? This team project was part of the Deep Learning SS23 course under the guidance of Professor Beggel. The main objective was to create an AI agent that could kick butt at the game of Othello. Have you heard of Othello? It is a

Playing Othello with a CNN

Board games and artificial intelligence have long been closely linked. Even in the early days of AI research in the 1950s, games like chess and checkers were used as testbeds for algorithmic decision-making. Because of their controlled environment with clear rules, they are ideal for developing AI. But advances in

Playing Othello with a Reinforcement Agent

Contents Introduction Environment and Setup Realization Conclusion References Introduction In the summer term 2023 we learned the basics of artificial neural networks in the course Deep Learning with Prof. Dr. Bastian Beggel. Depending on the field of application, different learning methods are used. There are three main categories: supervised, unsupervised

Audio Science Review Forum - Analyse eines Diskussionsforums

Dieser Blogbeitrag beschäftigt sich mit Data-Mining und beinhaltet die Erfassung, sowie Einordnung großer Datenmengen. Die Daten werden in ein Muster gebracht und in Beziehungen zueinander gestellt. Folgende Data-Mining-Techniken sind im Projekt umgesetzt worden: Datensatz erstellen (Datenabzug)Einstufung der DatenGruppierte Datensätze erstellenClusteringZeitreihenanalysenPrognosemethodenInterpretation der ausgewerteten DatenDie Ergebnisse dieser Analysen entstanden im Rahmen

Clustering

As a part of the “Data Science” master course at the University of Applied Sciences Kaiserslautern in the winter semester of 2022/23, we investigated clustering, which is a type of unsupervised machine learning. In this article, we provide an overview of what clustering is and where to apply clustering,

Das optimale Warenlager mit pgRouting und R

In diesem Artikel wird behandelt, wie wir anhand der vorliegenden Kundendaten ein neuen Lagerstandort optimal bestimmt habenund wie das Lager organisiert sein muss, um bei zukünftig gleichbleibenden Aufträgen schnell und effizient kommissionieren werden kann.Über das ProjektMotivationDer Artikel beinhaltet Ergebnisse aus unserer Projektarbeit im Fach Datascience aus dem Wintersemester 2022/

Warenkorb Analyse mit R

Die diversen Handelsgeschäfte, ob online oder lokal, besitzen meist eine Vielzahl von Daten, in denen sie das Kaufverhalten ihrer Kunden speichern. Insbesondere die Information über den Warenkorb eines Kunden ist besonders wertvoll. Durch die Daten können Kunden verglichen werden anhand der gekauften Artikeln. Das ist bereits Standard geworden und erlaubt

pgRouting - Eine Einführung

Ob Dijkstra, A-Star oder Johnson-Algorithmus, pgRouting reichert gewöhnliche Postgres-Datenbanken mit zahlreichen Funktionalitäten rund um's Routing und Netzwerkanalysen an. Und das Beste: pgRouting ist Open Source. Das nehmen wir zum Anlass, um einen kleinen Leitfaden für pgRouting-Einsteiger zu schreiben. Hierbei erklären wir im Wesentlichen ... ... wie man OSM-Daten in eine Postgres-Datenbank importiert.

Ein Reinforcement-Learning Agent lernt den Spieleklassiker Snake 🐍

Snake der Spieleklassiker der Millennials, auf jedem alten Nokia Handy vorhanden, begeisterte die kleine Apfel fressende Schlange Jung und Alt. Ziel des Spiel ist es die Schlange durch geschickten Input die zufällig erscheinenden Äpfel fressen zu lassen. Berührt die Schlange die Wand oder ihren eigenen Schwanz ist das Spiel vorbei.

Reinforcement Learning - Solving a Maze

As part of the master's course DeepLearning in the summer semester of 2022, various reinforcement learning algorithms were implemented using the Python programming language. The goal of the project was to solve a child's cube, or later a maze. The code for the project is available on GitHub. TL; DR;

U-Race

Unity Reinforcement Autonomous Car Environment Introduction to U-RaceIn order to work independently of Amazon's AWS DeepRacer and the associated 10-hour training limit, the U-Race framework was developed as part of the 'Deep Learning' course at Kaiserslautern University of Applied Sciences in the 2022 summer term. U-Race stands for 'Unity Reinforcement

AWS DeepRacer

Introduction to DeepRacerThis project was part of the course 'Deep Learning' at University of Applied Sciences Kaiserslautern. The topic of the summer term 2022 was 'Reinforcement Learning' and this is our approach to combine the topic with vehicles. After a research which projects are already available and fulfil our requirements,

TETRIS AI WITH REINFORCEMENT LEARNING

Today, artificial intelligence can be found almost everywhere, be it in image recognition, in parts of the car or in graphics cards. There are many different ways to implement artificial intelligence, and depending on the application, they work better or worse. To make it easier to imagine the principle of

Image Colorization

ImaginatorWeb site created using create-react-appClick here to open the demoThis project is about the colorization of black and white images. The goal of the project was to create a website where you can upload a black and white image and get the colored image back. The "Colorful Image Colorization" project

Chinese Whispers

The purpose of this project is to offer a web service where the features of the Google Cloud Platform can be explored. In particular the web service will use the Cloud Translation and Speech-to-Text API. The web service is called "Stille Post", which can be translated into "Chinese whispers", a

Project

Hochschulassistent Mario

This project was developed as part of the Deep Learning course at Kaiserslautern University of Applied Sciences in the summer semester of 2021. The project is a chatbot that primarily answers questions about Kaiserslautern University of Applied Sciences. The primary target groups are people interested in studying and current students.

Deep Learning