CS BSc Thesis Zoom Presentation 11 June 2021
Plats: Online via: https://lu-se.zoom.us/j/65275588287
Kontakt: birger [dot] swahn [at] cs [dot] lth [dot] se
Spara händelsen till din kalender
One Computer Science BSc thesis to be presented on 11 June via Zoom
Friday, 11 June there will be a bachelor thesis presentation in Computer Science at Lund University, Faculty of Engineering.
The presentation will take place via Zoom at: https://lu-se.zoom.us/j/65275588287
Please not that this presentation is for a bachelor thesis.
Note to potential opponents: Register as an opponent to the presentation of your choice by sending an email to the examiner for that presentation (firstname.lastname@example.org). Do not forget to specify the presentation you register for! Note that the number of opponents may be limited (often to two), so you might be forced to choose another presentation if you register too late. Registrations are individual, just as the oppositions are! More instructions are found on this page.
Presenter: Miroslava Brodlova
Title: Motivating a Conscious Machine with Novelty-Seeking
Examiner: Jacek Malec
Supervisors: Elin Anna Topp (LTH)
This bachelor's thesis aims to be a starting point for constructing motivation in a conscious machine through novelty-seeking mechanisms. Firstly, a limited literary review on how motivation functions in humans and animals is conducted to extract clues on how motivation may be implemented in a conscious program. Secondly, based on Lenore and Manuel Blum's model of a Conscious Turing Machine (CTM), basic components that theoretically support consciousness in non-biological matter are built. The CTM parts constructed include a Long Term Memory (LTM), a Short Term Memory (STM), Chunks and an Up- and Down-stream. Visual stimuli is then sent into the CTM-program in the form of pixels-values. Receiving pixels-values that are unchanging are in this project classified as a negative experience for the CTM, whereas pixel-values that vary over time are positive. The results highlight the difficulty in building a conscious machine with concurrent visual input. The project's resulting program was only able to effectively handle about 20000 LTM-processors (a far cry from the human brain's 86 billion neurons). More research is suggested that focuses on how the CTM can interact with visual stimuli and novelty-seeking algorithms for the purpose of finally achieving machine consciousness.
Link to presentation: https://lu-se.zoom.us/j/65275588287
Link to popular science summary: https://fileadmin.cs.lth.se/cs/Education/Examensarbete/Popsci/210611_11Brodlova.pdf