home.social

#cognitivesystems — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #cognitivesystems, aggregated by home.social.

fetched live
  1. Gordon Cheng and his team won an award at the half-marathon race for #humanoidrobots in Beijing! The robot completed the 21-kilometer course in 3 hours and 35 minutes, making it the best international team: go.tum.de/501882

    #robotics #cognitivesystems

    📷TUM

  2. Gordon Cheng and his team won an award at the half-marathon race for #humanoidrobots in Beijing! The robot completed the 21-kilometer course in 3 hours and 35 minutes, making it the best international team: go.tum.de/501882

    #robotics #cognitivesystems

    📷TUM

  3. Today at ICSR25 - 17th International Conference on Social Robotics, I presented the paper "RAGGAE for HERBS: Testing the Explanatory Performance of Ontology-powered LLMs for Human Explanation of Robotic Behaviors" by Agnese Augello, Edoardo Datteri, Antonio Lieto, Maria Rausa and Nicola Zagni

    #ICSR2025

    Title: RAGGAE for HERBS: Testing the Explanatory Performance of Ontology-powered LLMs for Human Explanation of Robotic Behaviors
    Abstract:
    In this work we present and test a RAG-based model called RAGGAE (i.e. RAG for the General Analysis of Explanans) tested in the context of Human Explanation of Robotic BehaviorS (HERBS).
    The RAGGAE model makes use of an ontology of explanations, enriching the knowledge of state of the art general purpose Large Language Models like Google Gemini 2.0 Flash, DeepSeek R1 and GPT-4o. The results show that the combination of a general LLM with a symbolic, and philosophically grounded, ontology can be a useful instrument to improve the investigation, identification and the analysis of the types of explanations that humans use to verbalize - and make sense of - the behavior of robotic agents.

    Paper: ciitlab.org/RAGGAE4HERBS_ICSR2

    System Live: ciitlab.org/agent.html

    Index Terms: #artificialintelligence #HumanRobotInteraction #explanation #largelanguaagemodels #rag #socialrobotics #robots #humanexplanation #cognitivesystems #LLM

    @academicchatter @cognition

  4. Today at ICSR25 - 17th International Conference on Social Robotics, I presented the paper "RAGGAE for HERBS: Testing the Explanatory Performance of Ontology-powered LLMs for Human Explanation of Robotic Behaviors" by Agnese Augello, Edoardo Datteri, Antonio Lieto, Maria Rausa and Nicola Zagni

    #ICSR2025

    Title: RAGGAE for HERBS: Testing the Explanatory Performance of Ontology-powered LLMs for Human Explanation of Robotic Behaviors
    Abstract:
    In this work we present and test a RAG-based model called RAGGAE (i.e. RAG for the General Analysis of Explanans) tested in the context of Human Explanation of Robotic BehaviorS (HERBS).
    The RAGGAE model makes use of an ontology of explanations, enriching the knowledge of state of the art general purpose Large Language Models like Google Gemini 2.0 Flash, DeepSeek R1 and GPT-4o. The results show that the combination of a general LLM with a symbolic, and philosophically grounded, ontology can be a useful instrument to improve the investigation, identification and the analysis of the types of explanations that humans use to verbalize - and make sense of - the behavior of robotic agents.

    Paper: ciitlab.org/RAGGAE4HERBS_ICSR2

    System Live: ciitlab.org/agent.html

    Index Terms: #artificialintelligence #HumanRobotInteraction #explanation #largelanguaagemodels #rag #socialrobotics #robots #humanexplanation #cognitivesystems #LLM

    @academicchatter @cognition

  5. 🧠 5,000 AI agent failures.
    🔁 42% now predicted before they happen.
    📉 Downtime slashed by 57%.

    Discover how agentic AI systems are evolving to forecast their own breakdowns—before executing a single action. A system-aware cognitive loop could be the future of intelligent decision-making.

    👉 Read Now:
    medium.com/@rogt.x1997/5-000-f

    #AI #AgenticAI #LLM #PredictiveAnalytics #FailureForecasting #CognitiveSystems #AIEngineering #MLOps #AIAgents
    medium.com/@rogt.x1997/5-000-f

  6. Happy birthday to Cognitive Design for Artificial Minds (lnkd.in/gZtzwDn3) that was released 4 years ago!

    Since then its ideas have been presented and discussed widely in the research fields of AI/Cognitive Science/Robotics and - nowadays - both the possibilities and the limitations of: #LLMs, #GenerativeAI and #ReinforcementLearning (already envisioned and discussed in the book) have become a common topic of research interests in the AI community and beyond.
    Similarly also the topic concerning the evaluation - in human-like and human-level terms - of the current AI systems has become a critical theme related to the problem Anthropomorphic interpretation of AI output (see e.g. lnkd.in/dVi9Qf_k ).
    Book reviews have been published on ACM Computing Reviews (2021) lnkd.in/dWQpJdkV and on Argumenta (2023): lnkd.in/derH3VKN

    I have been invited to present the content of the book in over 20 official scientific events in international conferences, Ph.D Schools in US, China, Japan, Finland, Germany, Sweden, France, Brazil, Poland, Austria and, of course, Italy.

    A news I am happy to share is that Routledge/Taylor & Francis contacted me few weeks ago for a second edition! Stay tuned!

    The #book is available in many webstores:
    - Routledge: lnkd.in/dPrC26p
    - Taylor & Francis: lnkd.in/dprVF2w
    - Amazon: lnkd.in/dC8rEzPi

    @academicchatter @cognition
    #AI #minimalcognitivegrid #CognitiveAI #cognitivescience #cognitivesystems

  7. Happy birthday to Cognitive Design for Artificial Minds (lnkd.in/gZtzwDn3) that was released 4 years ago!

    Since then its ideas have been presented and discussed widely in the research fields of AI/Cognitive Science/Robotics and - nowadays - both the possibilities and the limitations of: #LLMs, #GenerativeAI and #ReinforcementLearning (already envisioned and discussed in the book) have become a common topic of research interests in the AI community and beyond.
    Similarly also the topic concerning the evaluation - in human-like and human-level terms - of the current AI systems has become a critical theme related to the problem Anthropomorphic interpretation of AI output (see e.g. lnkd.in/dVi9Qf_k ).
    Book reviews have been published on ACM Computing Reviews (2021) lnkd.in/dWQpJdkV and on Argumenta (2023): lnkd.in/derH3VKN

    I have been invited to present the content of the book in over 20 official scientific events in international conferences, Ph.D Schools in US, China, Japan, Finland, Germany, Sweden, France, Brazil, Poland, Austria and, of course, Italy.

    A news I am happy to share is that Routledge/Taylor & Francis contacted me few weeks ago for a second edition! Stay tuned!

    The #book is available in many webstores:
    - Routledge: lnkd.in/dPrC26p
    - Taylor & Francis: lnkd.in/dprVF2w
    - Amazon: lnkd.in/dC8rEzPi

    @academicchatter @cognition
    #AI #minimalcognitivegrid #CognitiveAI #cognitivescience #cognitivesystems

  8. Glad and honored to have been invited to deliver a tutorial on "Cognitive Systems Design" to the 2025 IEEE
    CogSIMA Conference. The tutorial will cover the themes of the #book "Cognitive Design for Artificial Minds"
    doi.org/10.4324/9781315460536

    Link: edas.info/web/cogsima2025/tuto

    #AI #cognitivesystems

    @academicchatter @cognition

  9. Glad and honored to have been invited to deliver a tutorial on "Cognitive Systems Design" to the 2025 IEEE
    CogSIMA Conference. The tutorial will cover the themes of the #book "Cognitive Design for Artificial Minds"
    doi.org/10.4324/9781315460536

    Link: edas.info/web/cogsima2025/tuto

    #AI #cognitivesystems

    @academicchatter @cognition

  10. Melanie Mitchell @melaniemitchell
    (Santa Fe) at the AI Spotlight Seminars organized by the Italian Association for Artificial Intelligence (AI*IA) and the Society for the Study of Artificial Intelligence and Simulation of Behaviour (AISB), UK

    Her talk "AI's challenge of understanding the world" is available at:

    youtube.com/live/gRJgqSbk71o?f

    #AI #cogsci #humanlikeminds #humanlevelintelligence #Cognitivesystems #ArtificialIntelligence #cognition

    @academicchatter @cognition

  11. Melanie Mitchell @melaniemitchell
    (Santa Fe) at the AI Spotlight Seminars organized by the Italian Association for Artificial Intelligence (AI*IA) and the Society for the Study of Artificial Intelligence and Simulation of Behaviour (AISB), UK

    Her talk "AI's challenge of understanding the world" is available at:

    youtube.com/live/gRJgqSbk71o?f

    #AI #cogsci #humanlikeminds #humanlevelintelligence #Cognitivesystems #ArtificialIntelligence #cognition

    @academicchatter @cognition

  12. Ready for Institute 2024: the Schloss Dagstuhl School on Artificial and Human Intelligence starting tomorrow! Glad and honored to be invited here along with lecturers of the caliber of Barbara #Tversky, Thomas Eiter, Clayton Lewis, Alessandra Russo and many others.

    School: lnkd.in/dPetJmsN
    Program: lnkd.in/dsid4_TX

    #AI #generativeAI #cognitiveAI #Cognitivesystems #cognitivescience #cogsci #ArtificialIntelligence

    @academicchatter @cognition

  13. Ready for Institute 2024: the Schloss Dagstuhl School on Artificial and Human Intelligence starting tomorrow! Glad and honored to be invited here along with lecturers of the caliber of Barbara #Tversky, Thomas Eiter, Clayton Lewis, Alessandra Russo and many others.

    School: lnkd.in/dPetJmsN
    Program: lnkd.in/dsid4_TX

    #AI #generativeAI #cognitiveAI #Cognitivesystems #cognitivescience #cogsci #ArtificialIntelligence

    @academicchatter @cognition

  14. Molto onorato di aver ricevuto l'invito a tenere questo intervento (mercoledì prossimo, 8 maggio) da parte del Nexa Center for Internet & Society del Dipartimento di Automatica e Informatica (DAUIN) del Politecnico di Torino.

    Titolo: "Evitare la trappola comportamentista e la confusione tra sistemi human-like e human-level in Intelligenza Artificiale con la Minimal Cognitive Grid"
    Link: nexa.polito.it/mercoledi-172

    #AI #cognitiveAI #cognitivedesignforartificialminds #Cognitivesystems

  15. Molto onorato di aver ricevuto l'invito a tenere questo intervento (mercoledì prossimo, 8 maggio) da parte del Nexa Center for Internet & Society del Dipartimento di Automatica e Informatica (DAUIN) del Politecnico di Torino.

    Titolo: "Evitare la trappola comportamentista e la confusione tra sistemi human-like e human-level in Intelligenza Artificiale con la Minimal Cognitive Grid"
    Link: nexa.polito.it/mercoledi-172

    #AI #cognitiveAI #cognitivedesignforartificialminds #Cognitivesystems

  16. I am on today's edition of the PagerDuty podcast "Page it to the Limit"!

    Mandi and I were at AOL at the same time working in adjacent (but far-flung) teams, it was awesome getting to talk with her so many years later.

    #sre #operations #PagerDuty #ContinuousLearning #CognitiveSystems #resilience

    pageittothelimit.com/continuou

  17. I am on today's edition of the PagerDuty podcast "Page it to the Limit"!

    Mandi and I were at AOL at the same time working in adjacent (but far-flung) teams, it was awesome getting to talk with her so many years later.

    #sre #operations #PagerDuty #ContinuousLearning #CognitiveSystems #resilience

    pageittothelimit.com/continuou

  18. Talking about our newest paper because I think it's cool:

    A normal constraint satisfaction problem assumes a set of variables and looks for assignments to those variables so that the constraint is satisfied. Implicit in this framing is that you know what the variables are.

    As part of our research on how cognitive AI can have "the ability to follow the rules", one of the research problems we identified is approximately "learning the functions that map a constraint specification to potentially many places in an agent's state representations". Basically, we can't assume that map is "a given" in the agent's knowledge.

    This map is what enables an agent to evaluate whether and where the actual state complies with the constraint because it enables assignment of the state values to the variables in the disembodied constraint specification.

    We call it partial grounding of constraints and it looks somewhat like concept grounding or grounding in general.

    #AI #SymbolGrounding #CognitiveSystems #AcademicChatter

  19. Talking about our newest paper because I think it's cool:

    A normal constraint satisfaction problem assumes a set of variables and looks for assignments to those variables so that the constraint is satisfied. Implicit in this framing is that you know what the variables are.

    As part of our research on how cognitive AI can have "the ability to follow the rules", one of the research problems we identified is approximately "learning the functions that map a constraint specification to potentially many places in an agent's state representations". Basically, we can't assume that map is "a given" in the agent's knowledge.

    This map is what enables an agent to evaluate whether and where the actual state complies with the constraint because it enables assignment of the state values to the variables in the disembodied constraint specification.

    We call it partial grounding of constraints and it looks somewhat like concept grounding or grounding in general.

    #AI #SymbolGrounding #CognitiveSystems #AcademicChatter

  20. Glad and honored to be among the invited speakers of IJCLR 2023, the 3rd International Joint Conference on Learning & Reasoning, that will be held at the University of Bari ijclr2023.di.uniba.it/~ijclr20

    I'll be in the "Cognitive AI" track conferences.inf.ed.ac.uk/cogni

    #cognitiveAI #AI #research #cognitivesystems @academicchatter @cognition

  21. Glad and honored to be among the invited speakers of IJCLR 2023, the 3rd International Joint Conference on Learning & Reasoning, that will be held at the University of Bari ijclr2023.di.uniba.it/~ijclr20

    I'll be in the "Cognitive AI" track conferences.inf.ed.ac.uk/cogni

    #cognitiveAI #AI #research #cognitivesystems @academicchatter @cognition

  22. AIC 2023: 9th International Workshop on Artificial Intelligence and Cognition

    University of Bremen, Germany,14-15 September 2023

    Abstract Submission: 16 June, 2023

    Paper Submission: June 30th, 2023

    Website: ease-crc.org/aic-2023/

    AIC 2023 is the 9th international appointment of the Internat. Workshop Series on #ArtificialIntelligence and #Cognition aicworkshopseries.org/

    @academicchatter @cognition @acm_creativitycognition

    #cognitiveAI #cognitivesystems #cognitivescience #robotics

  23. AIC 2023: 9th International Workshop on Artificial Intelligence and Cognition

    University of Bremen, Germany,14-15 September 2023

    Abstract Submission: 16 June, 2023

    Paper Submission: June 30th, 2023

    Website: ease-crc.org/aic-2023/

    AIC 2023 is the 9th international appointment of the Internat. Workshop Series on #ArtificialIntelligence and #Cognition aicworkshopseries.org/

    @academicchatter @cognition @acm_creativitycognition

    #cognitiveAI #cognitivesystems #cognitivescience #robotics

  24. 🎙️ Bildung auf die Ohren: Die Zukunft der #KI im deutschen Schulwesen

    Dr. Caroline Hartmann spricht mit Frau Prof. Dr. Ute Schmid vom Fachbereich #CognitiveSystems, Otto-Friedrich-Universität Bamberg, über neue Anforderungen an zukünftige Curricula und Unterrichtsmethoden, einen niederschwelligen Einstieg für Lehrkräfte in das Programm ChatGPT sowie richtungsweisende kognitive Tutorsysteme für die Grundschule und die Sekundarstufe.

    bildungsserver.de/nachricht.ht

  25. 💻 Webinar hosted by Universidade Federal de Sao Paulo (Brazil) | ➡ about my book "Cognitive Design for Artificial Minds" (Routledge, 2021) amazon.com/dp/1138207950/, which explains the crucial role that human cognition research plays in the design and development of artificial intelligence systems.
    📌 Save the date:
    📅 TUE, APRIL 4, 2023
    ⏰ 6:00pm (CET) / 14h00 (Brazilian time)

    ▶️ Access:
    Unifesp Live Channel on Youtube Transmission: bit.ly/webinarLieto

    #AI #cognitivesystems #cognitiveAI

  26. 💻 Webinar hosted by Universidade Federal de Sao Paulo (Brazil) | ➡ about my book "Cognitive Design for Artificial Minds" (Routledge, 2021) amazon.com/dp/1138207950/, which explains the crucial role that human cognition research plays in the design and development of artificial intelligence systems.
    📌 Save the date:
    📅 TUE, APRIL 4, 2023
    ⏰ 6:00pm (CET) / 14h00 (Brazilian time)

    ▶️ Access:
    Unifesp Live Channel on Youtube Transmission: bit.ly/webinarLieto

    #AI #cognitivesystems #cognitiveAI

  27. This week, the book Cognitive Design for Artificial Minds (amazon.com/dp/1138207950/) reached the position #18 of the global chart on Amazon.com for the category "Artificial Intelligence"

    @Book review: computingreviews.com/review/re
    Editorial reviews: facebook.com/cognitivedesignfo

    The #book is available in many webstores:
    - Routledge: www.routledge.com/9781138207950
    - Taylor & Francis: doi.org/10.4324/9781315460536

    #artificialintelligence #cognitivesystems #cognitivescience #AI #cognitiveAI

  28. This week, the book Cognitive Design for Artificial Minds (amazon.com/dp/1138207950/) reached the position #18 of the global chart on Amazon.com for the category "Artificial Intelligence"

    @Book review: computingreviews.com/review/re
    Editorial reviews: facebook.com/cognitivedesignfo

    The #book is available in many webstores:
    - Routledge: www.routledge.com/9781138207950
    - Taylor & Francis: doi.org/10.4324/9781315460536

    #artificialintelligence #cognitivesystems #cognitivescience #AI #cognitiveAI

  29. I’m very excited about this paper we recently published at advances in #CognitiveSystems: arxiv.org/abs/2212.11937.

    We present a new framework for acquiring a language model from corpora that supports incremental updating. Our approach, which uses a kind of probabilistic discrimination tree representation, can dynamically grow and adjust its structure during online learning (beyond parameter tuning). Its modular knowledge should also let it avoid catastrophic forgetting effects. #ai #ml

  30. I’m very excited about this paper we recently published at advances in #CognitiveSystems: arxiv.org/abs/2212.11937.

    We present a new framework for acquiring a language model from corpora that supports incremental updating. Our approach, which uses a kind of probabilistic discrimination tree representation, can dynamically grow and adjust its structure during online learning (beyond parameter tuning). Its modular knowledge should also let it avoid catastrophic forgetting effects. #ai #ml

  31. I chatted with a futurist who disliked the term #AI preferring Intelligence Augmentation (#IA) because they view AI as a tool rather than a human replacement.

    Despite my #HCI upbringing, I found myself arguing that not all AI is augmentation. I noted that #CognitiveSystems is about understanding the nature of the mind and that I view #AI as exploring how minds can be built.

    I also referenced human-machine teaming (#HMT), which frames #AI as teammates not tools.

    What do you think?

  32. I chatted with a futurist who disliked the term #AI preferring Intelligence Augmentation (#IA) because they view AI as a tool rather than a human replacement.

    Despite my #HCI upbringing, I found myself arguing that not all AI is augmentation. I noted that #CognitiveSystems is about understanding the nature of the mind and that I view #AI as exploring how minds can be built.

    I also referenced human-machine teaming (#HMT), which frames #AI as teammates not tools.

    What do you think?

  33. Some photos from my invited tutorial on "Cognitive Design for Artificial Minds" at the 21st International Conference of the Italian Association for Artificial Intelligence in Udine: aixia2022.uniud.it/keynotes-an #AI #cognitivearchitectures #cognitiveAI #cybernetics #artificialintelligence #cognitivesystems #research #academiclife

  34. Some photos from my invited tutorial on "Cognitive Design for Artificial Minds" at the 21st International Conference of the Italian Association for Artificial Intelligence in Udine: aixia2022.uniud.it/keynotes-an #AI #cognitivearchitectures #cognitiveAI #cybernetics #artificialintelligence #cognitivesystems #research #academiclife

  35. #Introduction

    I study how collectives of agents (animals, neurons, mathematical structures) can solve problems.

    We also develop AI approaches based on Model Theory and Universal Algebra. They do not use optimization and are very transparent to mathematical analysis.

    #maths #mathematics #logic #algebra #CategoryTheory #types #ComputerScience

    #Neuroscience, #CollectiveBehavior #CollectiveIntelligence

    #MachineLearning #ComputerVision
    #SymbolicAI
    #CognitiveSystems
    #AI #ArtificialIntelligence

  36. #Introduction

    I study how collectives of agents (animals, neurons, mathematical structures) can solve problems.

    We also develop AI approaches based on Model Theory and Universal Algebra. They do not use optimization and are very transparent to mathematical analysis.

    #maths #mathematics #logic #algebra #CategoryTheory #types #ComputerScience

    #Neuroscience, #CollectiveBehavior #CollectiveIntelligence

    #MachineLearning #ComputerVision
    #SymbolicAI
    #CognitiveSystems
    #AI #ArtificialIntelligence

  37. #introduction

    I think about how a collective of agents (animals, neurons, mathematical structures) can solve problems. I am also interested in what it means to produce a good model and an understanding of something.

    I am excited to be here to learn and discuss.

    #Neuroscience, #CollectiveBehavior #CollectiveIntelligence

    #ComputerScience

    #maths #mathematics #logic #algebra #CategoryTheory #types

    #machinelearning #computervision
    #symbolicAI
    #CognitiveSystems
    #AI #ArtificialIntelligence

  38. #introduction

    I think about how a collective of agents (animals, neurons, mathematical structures) can solve problems. I am also interested in what it means to produce a good model and an understanding of something.

    I am excited to be here to learn and discuss.

    #Neuroscience, #CollectiveBehavior #CollectiveIntelligence

    #ComputerScience

    #maths #mathematics #logic #algebra #CategoryTheory #types

    #machinelearning #computervision
    #symbolicAI
    #CognitiveSystems
    #AI #ArtificialIntelligence

  39. Hi folks.

    I'm an AI guy and cognitive scientist who started out in academia #CognitiveSystems #ComputationalCreativity #NeurosymbolicIntegration but has been working in industry for the last couple of years #DigitalHealth #TrustworthyAI.

    I am actively involved in #AI #standardization on national (🇩🇪) and international (🇪🇺 and 🌍) level, and frequently dabble in public outreach and #scicom for general audiences.

  40. Interested in #CognitiveSystems?

    The Tenth Annual Conference on Advances in Cognitive Systems (cogsys.org/conference/2022/) will take place from 1PM on Saturday, November 19 into the late afternoon on Monday, November 21st. Additional workshops will occur on Tuesday, November 22nd.

    The conference will be hybrid and free to virtual attendees. Virtual registration is here: docs.google.com/forms/d/e/1FAI

    Here are the topics covered:

  41. #Introduction Hi, this is Antonio, an #AI and #CognitiveScience Researcher at the Department of Computer Science of the University of Turin (Italy) and an ACM Distinguished Speaker

    Research areas: Knowledge Representation and Reasoning in Humans and Machines, Language Technologies, #CognitiveSystems and Architectures, Persuasive Technologies.

    I have authored the book "Cognitive Design for Artificial Minds" (Routledge, 2021): routledge.pub/AntonioLieto

    More info here: antoniolieto.net