Sign in

ealonso.bsky.social

@ealonso.bsky.social
17 followers 13 following 6 posts
PostsRepliesMedia
Reposted by @ealonso.bsky.social
Esther Mondragón @e-mondragon.bsky.social · 21/03/2026
We then integrated SETs into a Structurally Enriched Trajectory Learning and Encoding (SETLE) architecture that incorporates a heterogeneous graph-based memory structure with multi-level relational dependencies, essential for task generalisation. www.sciencedirect.com/science/arti... 4/4
sciencedirect.com
A representational framework for learning and encoding structurally enriched trajectories in complex agent environments
The ability of artificial intelligence agents to make optimal decisions and generalise them to different domains and tasks is compromised in complex s…
153
ealonso.bsky.social @ealonso.bsky.social · 20/03/2026
Well done, Corina! Excellent paper!
011
Reposted by @ealonso.bsky.social
Esther Mondragón @e-mondragon.bsky.social · 10/02/2026
New preprint and simulator of associative learning attentional models. Have fun! 👁️ arxiv.org/abs/2602.07519 cal-r.org/index.php?id... #simulation #associative_learning #attention
arxiv.org
PALMS: Pavlovian Associative Learning Models Simulator
Simulations are an indispensable step in the cycle of theory development and refinement, helping researchers formulate precise definitions, generate models, and make accurate predictions. This paper i...
22314
Reposted by @ealonso.bsky.social
Mark Haselgrove @markhaselgrove.bsky.social · 10/02/2026
A very nice resource to have - Particularly happy to see it confirmed that my recent experiments on latent inhibition (and its reversal) cause a significant headache for Pearce-Hall and Hybrid models. psycnet.apa.org/record/2025-...
142
ealonso.bsky.social @ealonso.bsky.social · 05/10/2025
Thank YOU! It has been a lot of fun 😀
000
Reposted by @ealonso.bsky.social
Esther Mondragón @e-mondragon.bsky.social · 18/09/2025
@ealonso.bsky.social
021
Reposted by @ealonso.bsky.social
Esther Mondragón @e-mondragon.bsky.social · 01/10/2025
"Fascism is here, let’s not mistake ourselves. We need to know who the enemy [of freedom of speech] is" . @ealonso.bsky.social
121
Reposted by @ealonso.bsky.social
Alejandro Fábregas-Tejeda @alejandrofabregastejeda.com · 18/09/2025
The Centre for Logic and Philosophy of Science (CLPS) has just joined Bluesky! If you’re interested in #logic, epistemology, general #philsci, or the philosophy of the special sciences, consider following @clpskuleuven.bsky.social for updates on publications, events, and much more! 👇 #HPS #philsky
0255
Reposted by @ealonso.bsky.social
Index on Censorship @indexoncensorship.org · 11/09/2025
We’re thrilled to announce the speakers for our upcoming panel Truth, Trust & Tricksters in the age of AI: 🔹Kenneth Cukier (@kncukier.bsky.social) 🔹Timandra Harkness (@timandraharkness.bsky.social) 🔹Dr Eduardo Alonso (@citystgeorges.bsky.social) Join us: www.eventbrite.co.uk/e/truth-trus...
051
Reposted by @ealonso.bsky.social
Comics & AI: Critical Prompts @comicsandai.org · 04/09/2025
Finally, our Closing Keynote: Dr Ian Hague: Beyond #NoAI: How Accepting AI Might Change Comics #ComicsAndAI
Closing Keynote: Dr Ian Hague, Associate Dean of Research at London College of Communication, University of the Arts London: Beyond #NoAI: How Accepting AI Might Change Comics, stands front of lecture theatre behind pod, behind Ian two large screens with slides, Should we use AI? How should we use AI and for what purposes?
011
Reposted by @ealonso.bsky.social
Comics & AI: Critical Prompts @comicsandai.org · 04/09/2025
Now speaking: Viraj Joshi: Speculation as Resistance: Mundane machine intelligence, a narrowing of futures, and plural counter narratives #ComicsAndAI
Viraj Joshi stands at the front of the lecture theatre behind the pod, four screens visible, slide with "A narrowing of futures" as title
043
Reposted by @ealonso.bsky.social
Comics & AI: Critical Prompts @comicsandai.org · 04/09/2025
Jane Burns: Comics & AI: The Intersection with Social Innovation Education #ComicsAndAI
Jane Burns, The Intersection with Social Innovation Education, stands at front of lecture theatre, slides behind
022
Reposted by @ealonso.bsky.social
Comics & AI: Critical Prompts @comicsandai.org · 04/09/2025
Karrie Fransman on Creating IRL Comics for an AI Future! #ComicsAndAI
Karrie Fransman on Creating IRL Comics for an AI Future at the front of the lecture theatre, members of the audience visible, slides on screens
032
Reposted by @ealonso.bsky.social
Comics & AI: Critical Prompts @comicsandai.org · 04/09/2025
Dr Despoina Farmaki: The Ink Was Never Human: AI, Copyright, and Comics #ComicsAndAI
Dr Despoina Farmaki,  The Ink Was Never Human: AI, Copyright, and Comics stands at podium, title slides behind on screens
022
Reposted by @ealonso.bsky.social
Comics & AI: Critical Prompts @comicsandai.org · 04/09/2025
Jasleen Kandhari on Drawing the Line: AI & Ethics in Comic Book Character Design #ComicsAndAI
Jasleen Kandhari on Drawing the Line: AI & Ethics in Comic Book Character Design , she sits at the lecture theatre pod with screens behind her
022
Reposted by @ealonso.bsky.social
Comics & AI: Critical Prompts @comicsandai.org · 04/09/2025
It's been a thought-provoking and inspiring day; lots of interesting conversations, and we haven't been able to post here in real time! #ComicsAndAI
011
Reposted by @ealonso.bsky.social
Comics & AI: Critical Prompts @comicsandai.org · 04/09/2025
Now on: Dr Aaron Humphrey: Tracing nationalist legacies of generative AI #ComicsAndAI
Dr Aaron Humphrey at the front of the lecture theatre with two screens behind presenting on Tracing nationalist legacies of generative AI  with slide titled Image & Nation
031
Reposted by @ealonso.bsky.social
Comics & AI: Critical Prompts @comicsandai.org · 04/09/2025
We are back after the lunch break to begin the second part of the day! Now on Dr Linda Berube: “Intense Routes to Knowing”: Intersections between the Digital Sociology of Comics and AI #ComicsAndAI
Dr Linda Berube at the front of the lecture theatre with two screens behind her showing her title slide, “Intense Routes to Knowing”: Intersections between the Digital Sociology of Comics and AI
032
Reposted by @ealonso.bsky.social
Comics & AI: Critical Prompts @comicsandai.org · 04/09/2025
Dr Per Israelson on Speculative Affect and Generative AI: Reading Ilan Manouach’s manga Fastwalkers (2021) #ComicsAndAI
Dr Per Israelson on Speculative Affect and Generative AI: Reading Ilan Manouach’s manga Fastwalkers (2021)Dr Per Israelson on Speculative Affect and Generative AI: Reading Ilan Manouach’s manga Fastwalkers (2021)
022
Reposted by @ealonso.bsky.social
Comics & AI: Critical Prompts @comicsandai.org · 04/09/2025
Dr Julian Lawrence on Fun with AI: Digital Technology Through a Lens of Comics-Based Research #ComicsAndAI
Dr Julian Lawrence at lecture theatre pod, two screens behind with his slides, one comics panel on a white spaceDr Julian Lawrence at lecture theatre pod, two screens behind with his slides, two comics panels on a white space
032
Reposted by @ealonso.bsky.social
Comics & AI: Critical Prompts @comicsandai.org · 04/09/2025
Dr Giorgio Busi Rizzi on AI, comics, and creativity: or, why are we talking of ghosts in the machine again #ComicsAndAI
Dr Giorgio Busi Rizzi with his slides on the two screens behind him on image generation, memory and latent spaceDr Giorgio Busi Rizzi, slides behind on screens, title comics swiping
032
Reposted by @ealonso.bsky.social
Comics & AI: Critical Prompts @comicsandai.org · 04/09/2025
It's now @garethbrookes.bsky.social on The Autographic Witness in the Algorithm! #ComicsAndAI
Gareth Brooks at the podium with his title slides on the screens behind himGareth Brookes speaking with slides behind showing Palestine and Safe Area Gorazde graphic novel covers by Joe Sacco
032
Reposted by @ealonso.bsky.social
Comics & AI: Critical Prompts @comicsandai.org · 04/09/2025
And we are go! Professor Eduardo Alonso kicks off the day #ComicsAndAI
Professor Ed Alonso, screens behind with Gen 101 for Comics title slide Professor Ed Alonso, screens behind with slide with 1980s comics covers
042
Reposted by @ealonso.bsky.social
Esther Mondragón @e-mondragon.bsky.social · 21/08/2025
Available open access. www.sciencedirect.com/science/arti...
sciencedirect.com
Algebras of actions in an agent's representations of the world
Learning efficient representations allows robust processing of data, data that can then be generalised across different tasks and domains, and it is t…
063
Reposted by @ealonso.bsky.social
Esther Mondragón @e-mondragon.bsky.social · 11/08/2025
I am pleased to announce that this paper has been accepted for publication in Artificial Intelligence (AIJ)! 😊 arxiv.org/abs/2310.01536
arxiv.org
Algebras of actions in an agent's representations of the world
In this paper, we propose a framework to extract the algebra of the transformations of worlds from the perspective of an agent. As a starting point, we use our framework to reproduce the symmetry-base...
184
Reposted by @ealonso.bsky.social
Esther Mondragón @e-mondragon.bsky.social · 27/05/2025
Academia is rotten cal-r.org/mondragon/S7...
cal-r.org
Scripto_Academia_is_rotten
165
Reposted by @ealonso.bsky.social
Comics & AI: Critical Prompts @comicsandai.org · 15/05/2025
You are invited to a one-day multidisciplinary conference on the future of comics, technology, and creativity. Abstracts (200 words) + bios (100 words) due: 10 July 2025. Don’t miss this opportunity to rethink comics and AI with a multidisciplinary community! #CFP: comicsandai.org #ComicsStudies
comicsandai.org
Comics & AI: Critical Prompts
A multidisciplinary conference on the future of comics, technology, and creativity
21713
Reposted by @ealonso.bsky.social
Esther Mondragón @e-mondragon.bsky.social · 12/05/2025
This is to inform prospective students that I am no longer the programme director of MSc AI at City St. George's, University of London. Others, more aligned with the interests of the powers that be, will be in charge. Good luck, all.
media.tenor.com
a poster for disney + shows a man in a hooded cloak
ALT: a poster for disney + shows a man in a hooded cloak
244
Reposted by @ealonso.bsky.social
Esther Mondragón @e-mondragon.bsky.social · 11/05/2025
Glad to tell you that this paper has now been accepted for publication in Neural Networks. Well done @julian-jn.bsky.social !! 👏🏼🍻 arxiv.org/abs/2501.172...
arxiv.org
Advancing the Biological Plausibility and Efficacy of Hebbian Convolutional Neural Networks
The research presented in this paper advances the integration of Hebbian learning into Convolutional Neural Networks (CNNs) for image processing, systematically exploring different architectures to bu...
062
Reposted by @ealonso.bsky.social
Esther Mondragón @e-mondragon.bsky.social · 31/03/2025
Highly improved new version! Thanks all arxiv.org/abs/2501.172...
arxiv.org
Advancing the Biological Plausibility and Efficacy of Hebbian Convolutional Neural Networks
The research presented in this paper advances the integration of Hebbian learning into Convolutional Neural Networks (CNNs) for image processing, systematically exploring different architectures to bu...
022
Reposted by @ealonso.bsky.social
Berna Devezer @devezer.bsky.social · 18/03/2025
Happy "not an ass anymore"* day to me and all who celebrate! __________ A̶s̶s̶.̶ Prof.
554068
Reposted by @ealonso.bsky.social
Esther Mondragón @e-mondragon.bsky.social · 18/03/2025
New preprint with @corinacatarau.bsky.social and @ealonso.bsky.social from @citai.bsky.social: A representational framework for learning and encoding structurally enriched trajectories in complex agent environments arxiv.org/abs/2503.13194
arxiv.org
A representational framework for learning and encoding structurally enriched trajectories in complex agent environments
The ability of artificial intelligence agents to make optimal decisions and generalise them to different domains and tasks is compromised in complex scenarios. One way to address this issue has focuse...
31310
ealonso.bsky.social @ealonso.bsky.social · 01/03/2025
stoptrump.org.uk/petition-can...
stoptrump.org.uk
Petition: Cancel Trump’s state visit
Stop Trump Coalition
000
Reposted by @ealonso.bsky.social
Julian JN @julian-jn.bsky.social · 07/02/2025
🌟 Weekend Read: Advancing AI with Hebbian Learning! 🌟 Explore our latest research on integrating Hebbian learning into CNNs for more biologically realistic unsupervised models! 🔗 arxiv.org/abs/2501.17266 🔗 github.com/Julian-JN/Ad... 🌐 Follow @emp1.bsky.social & @citai.bsky.social for updates!
arxiv.org
Advancing the Biological Plausibility and Efficacy of Hebbian Convolutional Neural Networks
The research presented in this paper advances the integration of Hebbian learning into Convolutional Neural Networks (CNNs) for image processing, systematically exploring different architectures to bu...
194
Reposted by @ealonso.bsky.social
Esther Mondragón @e-mondragon.bsky.social · 28/01/2025
Malthus' principle for universities: growth until collapse. Method: Make executive teams unaccountable and wealthy, covert academics in dispensable and cheap labour, devalue curricula, abolish research, exalt intake and income and hire loyal incompetents.
media.tenor.com
a woman in a hijab says shame in front of a crowd of people
ALT: a woman in a hijab says shame in front of a crowd of people
011
Reposted by @ealonso.bsky.social
Julian JN @julian-jn.bsky.social · 30/01/2025
1. 🧠Excited to share my published paper "Advancing the Biological Plausibility and Efficacy of Hebbian Convolutional Neural Networks" with @emp1.bsky.social. Available from: arxiv.org/abs/2501.17266
284
Reposted by @ealonso.bsky.social
Julian JN @julian-jn.bsky.social · 30/01/2025
3. A Two-Phase Approach: 1️⃣Unsupervised Feature Learning: Our network first learns to recognise patterns and features from raw data without any labels through Hebbian learning with hard-winner-takes-all (hard-WTA) competition mechanisms.
142
Reposted by @ealonso.bsky.social
Esther Mondragón @e-mondragon.bsky.social · 30/01/2025
@citai.bsky.social
021
Reposted by @ealonso.bsky.social
Esther Mondragón @e-mondragon.bsky.social · 30/01/2025
New preprint from @citai.bsky.social and wonderful Julian @julian-jn.bsky.social
053
Reposted by @ealonso.bsky.social
Esther Mondragón @e-mondragon.bsky.social · 18/01/2025
Integrating Hebbian learning with competition mechanisms and CNNs
021
Reposted by @ealonso.bsky.social
Esther Mondragón @e-mondragon.bsky.social · 06/01/2025
An advance of a paper that will soon be available in ArXiv. All merit to my wonderful student @julian-jn.bsky.social ! I hope you enjoy it. We present an optimal architecture that significantly enhances recent research aimed at integrating Hebbian learning with competition mechanisms and CNNs. ➡️
Advancing the Biological Plausibility and Efficacy of Hebbian Convolutional Neural Networks by Julian Jimenez-Nimo and Esther Mondragón

The research presented in this paper advances the integration of Hebbian learning into Convolutional Neural Networks (CNNs) for image processing, systematically exploring different architectures to build an optimal configuration, adhering to biological tenability. Hebbian learning operates on local unsupervised neural information to form feature representations, providing an alternative to the popular but arguably biologically implausible and computationally intensive backpropagation learning algorithm. The suggested optimal architecture significantly enhances recent research aimed at integrating Hebbian learning with competition mechanisms and CNNs, expanding their representational capabilities by incorporating hard Winner-Takes-All (WTA) competition, Gaussian lateral inhibition mechanisms and Bienenstock–Cooper–Munro (BCM) learning rule in a single model. The resulting model achieved 76\% classification accuracy on CIFAR-10, rivalling its end-to-end backpropagation variant (77\%) and critically surpassing the state-of-the-art hard-WTA performance in CNNs of the same network depth (64.6\%) by 11.4\%.  Moreover, results showed clear indications of sparse hierarchical learning through increasingly complex and abstract receptive fields. In summary, our implementation enhances both the performance and the generalisability of the learnt representations and constitutes a crucial step towards more biologically realistic artificial neural networks.
1167
Reposted by @ealonso.bsky.social
Artificial Intelligence Research Centre, CitAI. @citai.bsky.social · 18/12/2024
Three Permanent/Full-time Lectureships in Computer Science are available at City St. Georges, University of London. More information can be found here: cit-ai.net/Academic-Job... To apply, visit www.city.ac.uk/about/jobs/a...
cit-ai.net
CitAI-Academic-Jobs
Website of the Artificial Reseach Centre, CitAI. Academic Jobs.
023
ealonso.bsky.social @ealonso.bsky.social · 20/09/2024
Wonderful to have participated in THE x Digital Science webinar on “Addressing evolving challenges to research security in the age of AI”. Full recording available at www.timeshighereducation.com/campus/addre... @citai.bsky.social @timeshighered.bsky.social
timeshighereducation.com
Addressing evolving challenges to research security in the age of AI
Watch the on-demand video of the Times Higher Education webinar on strengthening research security in the face of rapid technological changes
011
Reposted by @ealonso.bsky.social
Artificial Intelligence Research Centre, CitAI. @citai.bsky.social · 23/08/2024
We are delighted to announce the merger of City and St George’s (University of London)! CitAI is expanding. Stay tuned! 😜
media.tenor.com
angry birds movie poster that says it 's gonna be a lot of fun !
ALT: angry birds movie poster that says it 's gonna be a lot of fun !
032
Reposted by @ealonso.bsky.social
Esther Mondragón @e-mondragon.bsky.social · 11/06/2024
You don't want to miss Mel's @bayesianboy.bsky.social talk! Tomorrow at #CitAI_Seminars 👇👇
142
Reposted by @ealonso.bsky.social
Artificial Intelligence Research Centre, CitAI. @citai.bsky.social · 11/06/2024
Tomorrow, Wed 12 Jun, 16:00 BST, Mel Andrews @bayesianboy.bsky.social will tell us "What's scientific representation got to do with responsible AI?" Please get in touch with @emp1.bsky.social or the organisers at cit-ai.net/seminars.html for a Zoom link/pass. #CitAI_Seminars
031
Reposted by @ealonso.bsky.social
Artificial Intelligence Research Centre, CitAI. @citai.bsky.social · 29/05/2024
Wed 12 Jun, 16:00 BST, Mel Andrews @bayesianboy.bsky.social will tell us "What's scientific representation got to do with responsible AI?" Please get in touch with @emp1.bsky.social or the organisers at cit-ai.net/seminars.html for a Zoom link/pass. #CitAI_Seminars
cit-ai.net
CitAI-Seminars
Website of the Artificial Reseach Centre, CitAI. Seminars.
033
Reposted by @ealonso.bsky.social
Artificial Intelligence Research Centre, CitAI. @citai.bsky.social · 06/02/2024
We are pleased to announce that our AI@City has been accepted as one of the #AI UK Fringe events. Agenda and registration details: github.com/city-artific... March 6, 2024 City, University of London
074
Reposted by @ealonso.bsky.social
Artificial Intelligence Research Centre, CitAI. @citai.bsky.social · 31/01/2024
If you are thinking about learning Artificial Intelligence, this master's may be what you are looking for. A peek into our programme www.flipsnack.com/C5E97B77C6F/... To have a chat with the director f2f on Feb 7 from 5 to 7 at City, please register here: www.city.ac.uk/news-and-eve...
flipsnack.com
MSc Artificial Intelligence
Flipsnack is a digital catalog maker that makes it easy to create, publish and share html5 flipbooks. Upload a PDF or design from scratch flyers, magazines, books and more.
084
Reposted by @ealonso.bsky.social
Artificial Intelligence Research Centre, CitAI. @citai.bsky.social · 08/02/2024
Next #CitAI_seminars talk! Thu Feb 8 at 16:00 GTM. "Category Theory ∩ Deep Learning: Where are we, and where can we go?" by Bruno Gavranović (Mathematically Structured Programming Group) at the University of Strathclyde. cit-ai.net/seminars.html If you wish to Zoom in, let us know!
cit-ai.net
011