BEGIN:VCALENDAR
VERSION:2.0
PRODID:researchseminars.org
CALSCALE:GREGORIAN
X-WR-CALNAME:researchseminars.org
BEGIN:VEVENT
SUMMARY:Olle Häggström (Chalmers University of Technology\, Sweden)
DTSTART:20230821T140000Z
DTEND:20230821T150000Z
DTSTAMP:20260422T212750Z
UID:Wisla23/1
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/Wisla23/1/">
 AI risk and AI alignment</a>\nby Olle Häggström (Chalmers University of 
 Technology\, Sweden) as part of Mapping the Interdisciplinary Horizons of 
 AI: Safety\, Functional Programming\, Information Geometry\n\n\nAbstract\n
 The planetary dominance over other species that humanity has attained has 
 very little to do with muscular strength and physical endurance: it is all
  about intelligence. This makes the present moment in history\, when we ar
 e automating intelligence and handing over this crucial skill to machines\
 , the most important ever. The research area that has become known as AI a
 lignment deals with how to make sure that the first superintelligent machi
 nes have goals and values that are sufficiently aligned with ours and that
  sufficiently prioritize human flourishing. This needs to succeed\, becaus
 e otherwise we face existential catastrophe. In these lectures I will outl
 ine key challenges in AI alignment\, what is being done to solve them\, an
 d how all this relates to the breakneck speed at which AI is presently adv
 ancing.\n
LOCATION:https://researchseminars.org/talk/Wisla23/1/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Olle Häggström (Chalmers University of Technology\, Sweden)
DTSTART:20230821T153000Z
DTEND:20230821T163000Z
DTSTAMP:20260422T212750Z
UID:Wisla23/2
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/Wisla23/2/">
 AI risk and AI alignment</a>\nby Olle Häggström (Chalmers University of 
 Technology\, Sweden) as part of Mapping the Interdisciplinary Horizons of 
 AI: Safety\, Functional Programming\, Information Geometry\n\n\nAbstract\n
 The planetary dominance over other species that humanity has attained has 
 very little to do with muscular strength and physical endurance: it is all
  about intelligence. This makes the present moment in history\, when we ar
 e automating intelligence and handing over this crucial skill to machines\
 , the most important ever. The research area that has become known as AI a
 lignment deals with how to make sure that the first superintelligent machi
 nes have goals and values that are sufficiently aligned with ours and that
  sufficiently prioritize human flourishing. This needs to succeed\, becaus
 e otherwise we face existential catastrophe. In these lectures I will outl
 ine key challenges in AI alignment\, what is being done to solve them\, an
 d how all this relates to the breakneck speed at which AI is presently adv
 ancing.\n
LOCATION:https://researchseminars.org/talk/Wisla23/2/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Olle Häggström (Chalmers University of Technology\, Sweden)
DTSTART:20230822T140000Z
DTEND:20230822T150000Z
DTSTAMP:20260422T212750Z
UID:Wisla23/3
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/Wisla23/3/">
 AI risk and AI alignment</a>\nby Olle Häggström (Chalmers University of 
 Technology\, Sweden) as part of Mapping the Interdisciplinary Horizons of 
 AI: Safety\, Functional Programming\, Information Geometry\n\n\nAbstract\n
 The planetary dominance over other species that humanity has attained has 
 very little to do with muscular strength and physical endurance: it is all
  about intelligence. This makes the present moment in history\, when we ar
 e automating intelligence and handing over this crucial skill to machines\
 , the most important ever. The research area that has become known as AI a
 lignment deals with how to make sure that the first superintelligent machi
 nes have goals and values that are sufficiently aligned with ours and that
  sufficiently prioritize human flourishing. This needs to succeed\, becaus
 e otherwise we face existential catastrophe. In these lectures I will outl
 ine key challenges in AI alignment\, what is being done to solve them\, an
 d how all this relates to the breakneck speed at which AI is presently adv
 ancing.\n
LOCATION:https://researchseminars.org/talk/Wisla23/3/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Noémie  Combe (Max Planck Institute for Mathematics in Sciences\,
  Germany)
DTSTART:20230822T153000Z
DTEND:20230822T173000Z
DTSTAMP:20260422T212750Z
UID:Wisla23/4
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/Wisla23/4/">
 Exploring Information Geometry: Recent Advances and Connections to Topolog
 ical Field Theory</a>\nby Noémie  Combe (Max Planck Institute for Mathema
 tics in Sciences\, Germany) as part of Mapping the Interdisciplinary Horiz
 ons of AI: Safety\, Functional Programming\, Information Geometry\n\n\nAbs
 tract\nWith the rapid progress of machine learning\, artificial intelligen
 ce and data sciences\, the topic of information geometry is an important d
 omain of research. We aim at introducing the topic of information geometry
 \, as well as presenting some recent progress in this domain. Differential
  geometry and algebraic aspects shall be developed. The new tight relation
  between the information geometry and topological field theory will be dis
 cussed.\n
LOCATION:https://researchseminars.org/talk/Wisla23/4/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Noémie  Combe (Max Planck Institute for Mathematics in Sciences\,
  Germany)
DTSTART:20230824T140000Z
DTEND:20230824T160000Z
DTSTAMP:20260422T212750Z
UID:Wisla23/5
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/Wisla23/5/">
 Exploring Information Geometry: Recent Advances and Connections to Topolog
 ical Field Theory</a>\nby Noémie  Combe (Max Planck Institute for Mathema
 tics in Sciences\, Germany) as part of Mapping the Interdisciplinary Horiz
 ons of AI: Safety\, Functional Programming\, Information Geometry\n\n\nAbs
 tract\nWith the rapid progress of machine learning\, artificial intelligen
 ce and data sciences\, the topic of information geometry is an important d
 omain of research. We aim at introducing the topic of information geometry
 \, as well as presenting some recent progress in this domain. Differential
  geometry and algebraic aspects shall be developed. The new tight relation
  between the information geometry and topological field theory will be dis
 cussed.\n
LOCATION:https://researchseminars.org/talk/Wisla23/5/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Frédéric Barbaresco (Thales Land and Air Systems\, France)
DTSTART:20230828T140000Z
DTEND:20230828T150000Z
DTSTAMP:20260422T212750Z
UID:Wisla23/6
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/Wisla23/6/">
 Symplectic Foliation Structures of Information Geometry for Lie Groups Mac
 hine Learning</a>\nby Frédéric Barbaresco (Thales Land and Air Systems\,
  France) as part of Mapping the Interdisciplinary Horizons of AI: Safety\,
  Functional Programming\, Information Geometry\n\n\nAbstract\nWe present a
  new symplectic model of Information Geometry  based on Jean-Marie Souriau
 's Lie Groups Thermodynamics. Souriau model was initially described in cha
 pter IV “Statistical Mechanics” of his book “Structure of dynamical 
 systems” published in 1969. This model gives a  purely geometric charact
 erization of Entropy\, which appears as an invariant Casimir function in c
 oadjoint representation\, characterized by Poisson cohomology. Souriau has
  proved that we can associate a symplectic manifold to coadjoint orbits of
  a Lie group by the KKS 2-form (Kirillov\, Kostant\, Souriau 2-form) in th
 e affine case (affine model of coadjoint operator equivariance via Souriau
 's cocycle)\, that we have identified with Koszul-Fisher metric from Infor
 mation Geometry. Souriau established the generalized Gibbs density covaria
 nt under the action of the Lie group. The dual space of the Lie algebra fo
 liates into coadjoint orbits that are also the Entropy level sets that cou
 ld be interpreted in the framework of Thermodynamics by the fact that dyna
 mics on these symplectic leaves are non-dissipative\, whereas transversal 
 dynamics\, given by Poisson transverse structure\, are dissipative. We wil
 l finally introduce Gaussian distribution on the space of Symmetric Positi
 ve Definite (SPD) matrices\, through Souriau's covariant Gibbs density by 
 considering this space as the pure imaginary axis of the homogeneous Siege
 l upper half space where Sp(2n\,R)/U(n) acts transitively. We will also co
 nsider Gibbs density for Siegel Disk where SU(n\,n)/S(U(n)xU(n)) acts tran
 sitively. Gauss density of SPD matrices is then computed through Souriau's
  moment map and coadjoint orbits. Souriau’s Lie Groups Thermodynamics mo
 del will be further explored in European COST network CaLISTA and European
  HORIZON-MSCA project CaLIGOLA.\n
LOCATION:https://researchseminars.org/talk/Wisla23/6/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Frédéric Barbaresco (Thales Land and Air Systems\, France)
DTSTART:20230828T153000Z
DTEND:20230828T163000Z
DTSTAMP:20260422T212750Z
UID:Wisla23/7
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/Wisla23/7/">
 Symplectic Foliation Structures of Information Geometry for Lie Groups Mac
 hine Learning</a>\nby Frédéric Barbaresco (Thales Land and Air Systems\,
  France) as part of Mapping the Interdisciplinary Horizons of AI: Safety\,
  Functional Programming\, Information Geometry\n\n\nAbstract\nWe present a
  new symplectic model of Information Geometry  based on Jean-Marie Souriau
 's Lie Groups Thermodynamics. Souriau model was initially described in cha
 pter IV “Statistical Mechanics” of his book “Structure of dynamical 
 systems” published in 1969. This model gives a  purely geometric charact
 erization of Entropy\, which appears as an invariant Casimir function in c
 oadjoint representation\, characterized by Poisson cohomology. Souriau has
  proved that we can associate a symplectic manifold to coadjoint orbits of
  a Lie group by the KKS 2-form (Kirillov\, Kostant\, Souriau 2-form) in th
 e affine case (affine model of coadjoint operator equivariance via Souriau
 's cocycle)\, that we have identified with Koszul-Fisher metric from Infor
 mation Geometry. Souriau established the generalized Gibbs density covaria
 nt under the action of the Lie group. The dual space of the Lie algebra fo
 liates into coadjoint orbits that are also the Entropy level sets that cou
 ld be interpreted in the framework of Thermodynamics by the fact that dyna
 mics on these symplectic leaves are non-dissipative\, whereas transversal 
 dynamics\, given by Poisson transverse structure\, are dissipative. We wil
 l finally introduce Gaussian distribution on the space of Symmetric Positi
 ve Definite (SPD) matrices\, through Souriau's covariant Gibbs density by 
 considering this space as the pure imaginary axis of the homogeneous Siege
 l upper half space where Sp(2n\,R)/U(n) acts transitively. We will also co
 nsider Gibbs density for Siegel Disk where SU(n\,n)/S(U(n)xU(n)) acts tran
 sitively. Gauss density of SPD matrices is then computed through Souriau's
  moment map and coadjoint orbits. Souriau’s Lie Groups Thermodynamics mo
 del will be further explored in European COST network CaLISTA and European
  HORIZON-MSCA project CaLIGOLA.\n
LOCATION:https://researchseminars.org/talk/Wisla23/7/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Seth Baum (Global Catastrophic Risk Institute\, University of Camb
 ridge\, USA)
DTSTART:20230829T140000Z
DTEND:20230829T150000Z
DTSTAMP:20260422T212750Z
UID:Wisla23/10
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/Wisla23/10/"
 >Social and Philosophical Dimensions of AI Alignment</a>\nby Seth Baum (Gl
 obal Catastrophic Risk Institute\, University of Cambridge\, USA) as part 
 of Mapping the Interdisciplinary Horizons of AI: Safety\, Functional Progr
 amming\, Information Geometry\n\n\nAbstract\nSuccessful AI alignment requi
 res three steps: (1) concept(s) for what\, if anything\, to align AI to\; 
 (2) design(s) for how to implement the concept(s) in one or more AI system
 s\; and (3) the usage\, by human developers of AI systems\, of these desig
 n(s) instead of other\, less suitable design(s). Step (1) is mainly a matt
 er of moral philosophy\; step (2) is mainly a matter of computer science\;
  and step (3) is mainly a matter of social science and politics. My lectur
 e(s) will cover steps (1) and (3).\n
LOCATION:https://researchseminars.org/talk/Wisla23/10/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Seth Baum (Global Catastrophic Risk Institute\, University of Camb
 ridge\, USA)
DTSTART:20230829T153000Z
DTEND:20230829T163000Z
DTSTAMP:20260422T212750Z
UID:Wisla23/11
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/Wisla23/11/"
 >Social and Philosophical Dimensions of AI Alignment</a>\nby Seth Baum (Gl
 obal Catastrophic Risk Institute\, University of Cambridge\, USA) as part 
 of Mapping the Interdisciplinary Horizons of AI: Safety\, Functional Progr
 amming\, Information Geometry\n\n\nAbstract\nSuccessful AI alignment requi
 res three steps: (1) concept(s) for what\, if anything\, to align AI to\; 
 (2) design(s) for how to implement the concept(s) in one or more AI system
 s\; and (3) the usage\, by human developers of AI systems\, of these desig
 n(s) instead of other\, less suitable design(s). Step (1) is mainly a matt
 er of moral philosophy\; step (2) is mainly a matter of computer science\;
  and step (3) is mainly a matter of social science and politics. My lectur
 e(s) will cover steps (1) and (3).\n
LOCATION:https://researchseminars.org/talk/Wisla23/11/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Patrik Jansson (Chalmers University of Technology\, Sweden)
DTSTART:20230830T140000Z
DTEND:20230830T150000Z
DTSTAMP:20260422T212750Z
UID:Wisla23/14
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/Wisla23/14/"
 >Domain-Specific Languages of Mathematics</a>\nby Patrik Jansson (Chalmers
  University of Technology\, Sweden) as part of Mapping the Interdisciplina
 ry Horizons of AI: Safety\, Functional Programming\, Information Geometry\
 n\n\nAbstract\nThe main idea behind this minicoure is to encourage the stu
 dents to approach mathematical domains from a functional programming persp
 ective. We will learn about the language Haskell\; identify the main funct
 ions and types involved\; introduce calculational proofs\; pay attention t
 o the syntax of mathematical  expressions\; and\, finally\, to organize th
 e resulting functions and types in domain-specific languages.\n
LOCATION:https://researchseminars.org/talk/Wisla23/14/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Patrik Jansson (Chalmers University of Technology\, Sweden)
DTSTART:20230830T153000Z
DTEND:20230830T163000Z
DTSTAMP:20260422T212750Z
UID:Wisla23/15
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/Wisla23/15/"
 >Domain-Specific Languages of Mathematics</a>\nby Patrik Jansson (Chalmers
  University of Technology\, Sweden) as part of Mapping the Interdisciplina
 ry Horizons of AI: Safety\, Functional Programming\, Information Geometry\
 n\n\nAbstract\nThe main idea behind this minicoure is to encourage the stu
 dents to approach mathematical domains from a functional programming persp
 ective. We will learn about the language Haskell\; identify the main funct
 ions and types involved\; introduce calculational proofs\; pay attention t
 o the syntax of mathematical  expressions\; and\, finally\, to organize th
 e resulting functions and types in domain-specific languages.\n
LOCATION:https://researchseminars.org/talk/Wisla23/15/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Patrik Jansson (Chalmers University of Technology\, Sweden)
DTSTART:20230831T140000Z
DTEND:20230831T150000Z
DTSTAMP:20260422T212750Z
UID:Wisla23/16
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/Wisla23/16/"
 >Domain-Specific Languages of Mathematics</a>\nby Patrik Jansson (Chalmers
  University of Technology\, Sweden) as part of Mapping the Interdisciplina
 ry Horizons of AI: Safety\, Functional Programming\, Information Geometry\
 n\n\nAbstract\nThe main idea behind this minicoure is to encourage the stu
 dents to approach mathematical domains from a functional programming persp
 ective. We will learn about the language Haskell\; identify the main funct
 ions and types involved\; introduce calculational proofs\; pay attention t
 o the syntax of mathematical  expressions\; and\, finally\, to organize th
 e resulting functions and types in domain-specific languages.\n
LOCATION:https://researchseminars.org/talk/Wisla23/16/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Kazuki Okamura (Shizuoka University\, Japan)
DTSTART:20230831T153000Z
DTEND:20230831T163000Z
DTSTAMP:20260422T212750Z
UID:Wisla23/17
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/Wisla23/17/"
 >Metrization of powers of the Jensen-Shannon divergence [part of Workshop]
 </a>\nby Kazuki Okamura (Shizuoka University\, Japan) as part of Mapping t
 he Interdisciplinary Horizons of AI: Safety\, Functional Programming\, Inf
 ormation Geometry\n\n\nAbstract\nMetrization of statistical divergences is
  useful in both the theoretical and practical aspects. \nConsidering the f
 ractional powers of statistical divergences is one way to obtain metrics a
 ssociated with divergences. \nWith this motivation\, Osán\, Bussandri\, a
 nd Lamberti (2018) considered metrizations for the fractional powers of th
 e Jensen-Shannon divergences between multinomial distributions and gave an
  open problem. \nWe give an affirmative answer to their conjecture. \nOur 
 method is also applicable to fractional powers of f-divergences between th
 e Cauchy distribution.\n
LOCATION:https://researchseminars.org/talk/Wisla23/17/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Dmitri Alekseevsky (University of Hradec Králové\, Czech Republi
 c)
DTSTART:20230823T140000Z
DTEND:20230823T150000Z
DTSTAMP:20260422T212750Z
UID:Wisla23/18
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/Wisla23/18/"
 >Neurogeometry of Vision and Information Geometry of Homogeneous Convex Co
 nes</a>\nby Dmitri Alekseevsky (University of Hradec Králové\, Czech Rep
 ublic) as part of Mapping the Interdisciplinary Horizons of AI: Safety\, F
 unctional Programming\, Information Geometry\n\n\nAbstract\nThese lectures
  will provide a comprehensive overview of information processing. We will 
 start with information processing in early vision in static and geometric 
 models of the primary visual cortex. Then\, we will explore information pr
 ocessing in vision in dynamics. Finally\, we gonna talk about the informat
 ion geometry of Chentsov-Amari and homogeneous convex cones.\n
LOCATION:https://researchseminars.org/talk/Wisla23/18/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Dmitri Alekseevsky (University of Hradec Králové\, Czech Republi
 c)
DTSTART:20230823T153000Z
DTEND:20230823T163000Z
DTSTAMP:20260422T212750Z
UID:Wisla23/19
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/Wisla23/19/"
 >Neurogeometry of Vision and Information Geometry of Homogeneous Convex Co
 nes</a>\nby Dmitri Alekseevsky (University of Hradec Králové\, Czech Rep
 ublic) as part of Mapping the Interdisciplinary Horizons of AI: Safety\, F
 unctional Programming\, Information Geometry\n\n\nAbstract\nThese lectures
  will provide a comprehensive overview of information processing. We will 
 start with information processing in early vision in static and geometric 
 models of the primary visual cortex. Then\, we will explore information pr
 ocessing in vision in dynamics. Finally\, we gonna talk about the informat
 ion geometry of Chentsov-Amari and homogeneous convex cones.\n
LOCATION:https://researchseminars.org/talk/Wisla23/19/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Frank Nielsen (Sony Computer Science Laboratories\, Japan)
DTSTART:20230829T070000Z
DTEND:20230829T090000Z
DTSTAMP:20260422T212750Z
UID:Wisla23/20
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/Wisla23/20/"
 >Introduction to Information Geometry\, Recent Advances\, and Applications
 </a>\nby Frank Nielsen (Sony Computer Science Laboratories\, Japan) as par
 t of Mapping the Interdisciplinary Horizons of AI: Safety\, Functional Pro
 gramming\, Information Geometry\n\nAbstract: TBA\n
LOCATION:https://researchseminars.org/talk/Wisla23/20/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Michael Roop (Chalmers University of Technology\, Sweden)
DTSTART:20230831T150000Z
DTEND:20230831T153000Z
DTSTAMP:20260422T212750Z
UID:Wisla23/21
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/Wisla23/21/"
 >Lie-Poisson methods for incompressible magnetohydrodynamics on the sphere
  [part of Workshop]</a>\nby Michael Roop (Chalmers University of Technolog
 y\, Sweden) as part of Mapping the Interdisciplinary Horizons of AI: Safet
 y\, Functional Programming\, Information Geometry\n\n\nAbstract\nWe presen
 t a novel structure preserving numerical method for Lie-Poisson systems on
  the dual of semidirect product Lie algebras. The method preserves the und
 erlying geometry\, namely the Lie-Poisson structure and all the Casimirs\,
  and nearly preserves the Hamiltonian function. We illustrate the method o
 n two models describing the motion of magnetic fluids\, the incompressible
  magnetohydrodynamics equations and the Alfvén wave turbulence equations.
  For the latter case\, we reveal the formation of large scale quasi-period
 ic vortex blob dynamics.\n
LOCATION:https://researchseminars.org/talk/Wisla23/21/
END:VEVENT
END:VCALENDAR
