talk-data.com
Activities tracked
6
Data Science Retreat presents 6 Machine Learning prototypes and projects by Batch 39 participants. The event is free to attend and thanks to KI-Servicezentrum by Hasso-Plattner-Institut für Digital Engineering GmbH for hosting us.
Agenda: 17:30 - Drinks and Networking
18:00 - Welcome & Introduction
Followed by Project Presentations
Project Ideas:
1. DanceBits: Choreography Video Segmentation Project by Cristina Melnic, Arpad Dusa and Paras Mehta
DanceBits is an innovative machine learning application designed to automatically segment choreography videos into component moves. Our goal is to create an interactive learning platform for dance instruction and analysis, making dance education more accessible and engaging.
2. Application that assists musicians/performers in performing live concerts. Project by Khaled Hassan
The project aims to develop an application that assists musicians/performers in performing live concerts. So the model takes in a "sequence" of notes or rhythms from the performer and keeps generating and playing music/rhythms in the same style live on stage. It can also add other instruments and harmonies that fit with the main line per request. So the end result would be an AI-assisted music concert.
3. Autonomous Security Robot Project by Zain Elabedeen
The autonomous security robot on 4 wheels is designed to provide security monitoring and threat detection. It can map its environment and move around autonomously, patrol specific areas or objects, detect and respond to threats. The robot monitors its surroundings for potential threats, such as intruders or suspicious items. It can be set up to automatically guard a certain area, protect a person, or watch over an object
4. Enhancing Pedestrian Safety in Autonomous Driving Using YOLO-Based Real-Time Object Detection Project by Ni Dang
Develop a YOLO-based object detection system specifically optimized for pedestrian detection in urban settings. The system will focus on real-time detection of pedestrians in different environments.
5. AI assistant for mental health Project by Anke Braun
This project aims to leverage retrieval augmented generation (RAG) and fine-tuning of LLMs to create an AI-based assistant for mental health, which could be used to support a psychotherapist.
6. Cucumber Intelligence Project by Björn Opitz
The "Cucumber Intelligence" project aims to automate cucumber harvesting surveillance. The project involves capturing thousands of images and videos of cucumbers on conveyor belts for AI-based detection and counting using a YOLO-based model.
20:00 - Open for networking
20:30 - Wrap up
See you all at the event.
Sessions & talks
Showing 1–6 of 6 · Newest first
This project aims to leverage retrieval augmented generation (RAG) and fine-tuning of LLMs to create an AI-based assistant for mental health, which could be used to support a psychotherapist.
The project aims to develop an application that assists musicians/performers in performing live concerts. So the model takes in a sequence of notes or rhythms from the performer and keeps generating and playing music/rhythms in the same style live on stage. It can also add other instruments and harmonies that fit with the main line per request. So the end result would be an AI-assisted music concert.
The autonomous security robot on 4 wheels is designed to provide security monitoring and threat detection. It can map its environment and move around autonomously, patrol specific areas or objects, detect and respond to threats. The robot monitors its surroundings for potential threats, such as intruders or suspicious items. It can be set up to automatically guard a certain area, protect a person, or watch over an object
The Cucumber Intelligence project aims to automate cucumber harvesting surveillance. The project involves capturing thousands of images and videos of cucumbers on conveyor belts for AI-based detection and counting using a YOLO-based model.
DanceBits is an innovative machine learning application designed to automatically segment choreography videos into component moves. Our goal is to create an interactive learning platform for dance instruction and analysis, making dance education more accessible and engaging.
Develop a YOLO-based object detection system specifically optimized for pedestrian detection in urban settings. The system will focus on real-time detection of pedestrians in different environments.