Johan Pouwelse

- Please write a progress update **before** the meeting, this did not happen multiple times. - Keep laser-sharp focus on progress. Why did you revisit the non-duplicates non-converging approach? -...

Amazing related work by Google Research found by our phd student Petru: https://github.com/Tribler/tribler/issues/7586#issuecomment-1790956120 _[Transformer Memory as a Differentiable Search Index](https://arxiv.org/pdf/2202.06991.pdf). The paper argues that instead of using a dual-encoder method...

- making progress! - [X] Got 96% experiment, thesis is out of the risky zone - [X] Explored various options, BERT, Word2Vec, pre-trained models, etc. - [ ] Turn the...

- First master thesis text :tada: - Add an architecture Figure and section with "Architecture and Design" - Realised today the URL is not embedded, model output is embedding of...

- Not as much progress as hoped - Use a pre-trained model - Please explore using Google Colab with NanoT5 using Pytorch and/or local GPU - Fine-tuning of video IDs...

- This level of progress is not leading to a master thesis - Please [contact Petru](https://github.com/Tribler/tribler/issues/7586), as suggested on 8 Nov

- Bug FIXED by @pneague (special token skip, too low epochs)! Great step forward with thesis! - Master thesis level! :tada: - Please label your lines within your figures -...

@inekestijnman @herrJones We making progress trying to fix this one. Thank you for reporting! We now trying to switch 'reactor core' to see if that was the issue. Coming days...

btw please register today at: https://mare.ewi.tudelft.nl/ "decentralised learning" as the draft thesis project title. Me as advisor please. (just a tentative commitment, gives me teaching credits) Status: Survey started, looked...

- nice progress - ```panoramic view of the academic, technological, and practical landscape surrounding public key cryptography and its integration into digital infrastructure``` Solid idea :rocket: - What problem does...