Topic outline

  • This lecture promotes understanding of good practices for Ambient Intelligence, including data collection, training, machine learning with noisy and inaccurate data.

    In particular, we focus on feature extraction/ feature subset selection, handling high dimensional data, ANN + Deep Learning, Probabilistic graphical models, Topic models; as well as Unsupervised learning and clustering, Anomaly detection and Recommender systems.

    The lecture has a modular structure and is project-based and foster hands-on experience with machine learning approaches on relevant data sets.

     

    info

    Lecture Schedule (T6 & zoom):
    Friday, 13.01.2023, 14:15 - Organization: slidestopics; non-edited video (https://www.dropbox.com/s/tcyf8qovhwrxylf/AmbientIntelligence2023-00.mp4?dl=0)
    Wednesday, 18.01.2023, 14:15 - Introduction: slides; non-edited video (https://www.dropbox.com/s/gm2xcfyb7px3v7l/AmI_2023-01.mp4?dl=0)
    Friday, 20.01.2023, 14:15 - Group allocation
    Wednesday, 25.01.2023, 14:15 - Data collection and Training: slides; non-edited video (https://www.dropbox.com/s/v43f5m6omf0xupo/AmI_2023-02.mp4?dl=0) 
    Friday, 27.01.2023, 14:15 -  Tutorial training (Martin - Diffusion models)
    Wednesday, 01.02.2023, 14:15 - Usable Security - Fuzzy Cryptography: slides; non-edited video (https://www.dropbox.com/s/j43pxnqlplemgqf/AmI_2023-03.mp4?dl=0)
    Friday, 03.02.2023, 14:15 -  No lecture
    Wednesday, 08.02.2023, 14:15 -  Sensing with mmWave radar devices: slides; non-edited video (https://www.dropbox.com/s/d7rix3x0ek1n7am/AmI_2023-04.mp4?dl=0)
    Friday, 10.02.2023, 14:15 -  Tutorial training (Martin - Diffusion models; Andrei - GPT-3.5; Behzad - Neural Architecture Search)
    Wednesday, 15.02.2023, 14:15 - No lecture
    Friday, 17.02.2023, 14:15 - Tutorial training (Behzad - Neural Architecture Search)
    Wednesday, 01.03.2023, 14:15 - Machine learning: slides
    Friday, 03.03.2023, 14:15 - Tutorial training (GPT - 3.5 - Andrei)
    Wednesday, 08.03.2023, 14:15 - Invited talk (Bosch Sensortec)
    Friday, 10.03.2023, 14:15 - Tutorial training (Lingyun - Probabilistic Machine Learning / Jelin - Machine learning models for constrained hardware)
    Wednesday, 15.03.2023, 14:15 - No lecture
    Friday, 17.03.2023, 14:15 -  Tutorial training (Jelin - Machine learning models for constrained hardware)
    Wednesday, 22.03.2023, 14:15 - Tutorial (Diffusion Models / Neural Architecture Search)
    Friday, 24.03.2023, 14:15 - Tutorial (GPT / Probabilistic Machine learning / Machine learning models for constrained hardware)
    Wednesday, 29.03.2023, 14:15 - Invited talk (Nokia Bell-labs)
    Friday, 31.03.2023, 14:15 - Poster presentations

    Tutorial topics (tbc):
    • Neural Architecture search (Behzad Mahboob)
    • Creativity in AI
    • Capsule networks
    • GPT-3.5
    • Diffusion models
    • Semantic communication
    • Contrastive learning

    Modules:
    Modules can be selected in any combination. Credits are granted according to the completion of modules. 

    • Video lectures (0 cr): Video lectures are provided for some topics to further the learning of the topic.
    • Lectures (1 cr): Physical attendance and active participation in at least 10 contact teaching sessions
    • Tutorials (2cr, graded): Preparation, training and presentation in front of the class of an in-depth tutorial on a specialized theme
    • Projects (4cr, graded): Guided Project work in teams of students on a research or industry-relevant topic/data. Video-status reports throughout the project duration and final presentation in form of a poster.
    • Oral exam (1cr, graded): Individual technical discussion (20 minutes) on the topics taught in the class
    Grading rules:
    grading
    The lecture will feature invited lectures given by international experts from industry and academia.