Andrii Krutsylo

News

2024

2024.04 🇬🇧 I will be presenting the progress of my work on gradient-free optimization for CL at BioInference at the University of Warwick, UK on June 6th. It will be a poster titled "The Forward-Forward Algorithm: Biologically Inspired Optimization for Continual Learning"!
2024.02 Thanks to a grant from the Python Software Foundation, I will be attending PyCon US 2024 remotely!
2024.01 🏆 My paper "Batch Sampling for Experience Replay" won the Best Paper Award at the CODS-COMAD!

2023

2023.11 🇪🇸 My paper "Evaluating Knowledge Retention in Continual Learning" has been accepted for poster presentation at the 39th ACM/SIGAPP Symposium On Applied Computing.
2023.11 I was invited to remotely speak at the ICCSCT on November 24th about performance metrics in CL ("Evaluating Continual Learning: A Detailed Survey of Performance Metrics").
2023.11 🇫🇷 The 3rd International Workshop on AI for Robotics at NAVER LABS Europe in Grenoble gave me the opportunity to present my preliminary results on training batch expansion for continual learning on 16 November.
2023.11 🇮🇳 My paper "Batch Sampling for Experience Replay" has been accepted for the CODS-COMAD conference and I will be presenting it in Bangalor, India sometime between 4 and 7 January.
2023.10 🇨🇦 I will present the current state of my dissertation at the AAAI-24 Doctoral Consortium on February 21, 2024 in Vancouver, Canada.
2023.10 I got the travel grant from G-Research! Every month they support the most promising PhD students or postdocs in quantitative disciplines from any European country with grants of £2,000. Here is the link to the programme description.
2023.09 I will be virtually delivering a talk on 'Memory Management Strategies in Replay-Based Continual Learning Beyond Reservoir Sampling' at the Continual AI UnConference on October 19. Registration is absolutely free!
2023.09 🇵🇱 My poster submission has been accepted for the ML in PL Conference, which will take place in Warsaw from October 26 to 29.
2023.05 🇬🇧 On June 30th, I will be delivering a contributed talk on the topic of Continual Learning as an Affordable ML tool at The First Edinburgh Workshop on Affordable Machine Learning. This event is hosted by The Schools of Informatics and Engineering at The University of Edinburgh.
2023.02 🇮🇹 For the next ~~two~~ three months, I will be conducting research at the Pervasive AI Laboratory at the University of Pisa in Italy, as part of the TAILOR grant.

2022

2022.12 🇺🇸 I will be at the HICSS conference in Lahaina, Hawaii (USA) from January 2, 2023 to January 7.
2022.12 My virtual registration for NeurIPS was covered by the organizers of Robot Learning Workshop. Thank you!
2022.11 HOSTKEY, a web services provider from the Netherlands, gave me access to a server with configuration 8 vCore/32Gb/240Gb vHDD/VGPU RTX A4000 as a computing grant for continual learning research. Awesome!
2022.10 🇧🇪 I visited Bruges (Belgium) with a spotlight poster presentation at the ESANN conference October 2-7.
2022.09 I started my mentorship with the RCDC@SIGGRAPH Undergraduate Mentorship Program.
2022.09 I successfully passed my mid-term evaluation of the doctoral studies.
2022.08 "Hebbian Continual Representation Learning" is accepted in HICSS.
2022.07 I was selected as a mentor at Neuromatch Academy for the online Deep Learning course in Pytorch.
2022.05 "Diverse Memory for Experience Replay in Continual Learning" is accepted in ESANN and selected for the spotlight presentation.

Contact

e-mail: (public key)

        GPG
        pub   rsa4096 2022-09-18 [SC]
              EA8670F4553BA6CD1C8F87A9BC5EC2F8BCE9C8A5
        uid           [ultimate] Andrii Krutsylo
        sub   rsa4096 2022-09-18 [E]

    GPG
    pub   rsa4096 2022-09-18 [SC]
        EA8670F4553BA6CD1C8F87A9BC5EC2F8BCE9C8A5
    uid           [ultimate] Andrii Krutsylo
    sub   rsa4096 2022-09-18 [E]

Security

The authenticity of any (or at least main) page on this website can be verified using GPG:

        # import my public key
        gpg --keyserver keyserver.ubuntu.com --recv-keys 910e309c330be661
        # download path_to_page to verify
        wget -q https://krutsylo.neocities.org/index.html
        # download signature path_to_page.asc
        wget -q https://krutsylo.neocities.org/index.html.asc
        # verify
        gpg --verify index.html.asc index.html

with expected output:

        gpg: Good signature from "Andrii Krutsylo"

     # import my public key
     gpg --keyserver keyserver.ubuntu.com --recv-keys 910e309c330be661
     # download path_to_page to verify
     wget -q https://krutsylo.neocities.org/index.html
     # download signature path_to_page.asc
     wget -q https://krutsylo.neocities.org/index.html.asc
     # verify
     gpg --verify index.html.asc index.html

with expected output:

     gpg: Good signature from "Andrii Krutsylo"

I am using freeTSA.org time stamp authority.

License

All texts, images and animations on website (toplevel directory) for which a separate license is not specified are licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
All source code on website (toplevel directory) is supplied as is, without any warranty and is licensed under The GNU General Public License v3.0 unless another license is specified.

Teaching

Publications


	Evaluating Knowledge Retention in Continual Learning
	SAC 2024
	Andrii Krutsylo
	PDF Poster


	Batch Sampling for Experience Replay
	CODS-COMAD 2024 (Best Paper Award)
	Andrii Krutsylo
	PDF Poster


	Hebbian Continual Representation Learning
	HICSS 2022
	Paweł Morawiecki, Andrii Krutsylo, Maciej Wołczyk, Marek Śmieja
	PDF Short


	Diverse Memory for Experience Replay in Continual Learning
	ESANN 2022 (spotlight)
	Andrii Krutsylo, Paweł Morawiecki
	PDF Poster


	Remember More by Recalling Less: Investigating the Role of Batch Size in Continual Learning with Experience Replay (Student Abstract)
	AAAI 2021
	Maciej Wołczyk, Andrii Krutsylo
	PDF