It looks like you're new here. If you want to get involved, click one of these buttons!

- All Categories 2.4K
- Chat 502
- Study Groups 21
- Petri Nets 9
- Epidemiology 4
- Leaf Modeling 2
- Review Sections 9
- MIT 2020: Programming with Categories 51
- MIT 2020: Lectures 20
- MIT 2020: Exercises 25
- Baez ACT 2019: Online Course 339
- Baez ACT 2019: Lectures 79
- Baez ACT 2019: Exercises 149
- Baez ACT 2019: Chat 50
- UCR ACT Seminar 4
- General 73
- Azimuth Code Project 110
- Statistical methods 4
- Drafts 10
- Math Syntax Demos 15
- Wiki - Latest Changes 3
- Strategy 113
- Azimuth Project 1.1K
- - Spam 1
- News and Information 148
- Azimuth Blog 149
- - Conventions and Policies 21
- - Questions 43
- Azimuth Wiki 718

Options

TGSI2017, to be held 27 August-1 September 2017 at CIRM, is dedicated to the geometrical and topological foundations of information theory. It will complement the 2017, 2016, 2015 and 2013 edition of "Geometric Science of Information" and "Information Geometry and its Applications IV", by focusing on the advances of entropy and information functions in probability, geometry, homology, algebra, category theory and their expression in physic and data analysis.

http://forum.cs-dc.org/topic/361/tgsi2017-presentation-organisation-abstract-submission

A preliminary program can be found here:

http://forum.cs-dc.org/topic/387/tgsi2017-preliminary-program

The sessions are :

Session 1: Information-Theoretic Geometry of Metric Measure Spaces (particular and general).

Session 2: Information and Topology

Session 3: Classical/Stochastic Geometric Mechanics and Lie Group Thermodynamics /Statistical Physics

Session 4: Geometry of Quantum States and Quantum Correlations

Session 5: Quantum States of Geometry and Geometry of Quantum States.

Session 6: Geometric Statistics on Manifolds and Shape Spaces.

Session 7: Geometry of Information for Neural Networks, Machine Learning, and Artificial Intelligence.

## Comments

Nice! I moved this post to "News and information", since you are not adding information to the Azimuth Wiki pages on "Mathematical methods", but instead passing on an announcement. I may post a version of this on the blog.

`Nice! I moved this post to "News and information", since you are not adding information to the Azimuth Wiki pages on "Mathematical methods", but instead passing on an announcement. I may post a version of this on the blog.`

Yes, thanks and sorry, I am beginner and a bit confused on where to post things. The conference webpages contain only few scientific info with abstract resuming the motivations of the sessions for the moment. In the future, they will be completed with the videos of each conferences and all related documents (PDF).

`Yes, thanks and sorry, I am beginner and a bit confused on where to post things. The conference webpages contain only few scientific info with abstract resuming the motivations of the sessions for the moment. In the future, they will be completed with the videos of each conferences and all related documents (PDF).`

I am very happy to see this Pierre. I have seen that the bulk of the computing community makes do with crude distance measures, when analyzing high-dimensional datasets, then uses a brute-force approximation. Worst; people in Computer Science seem to completely lack the sophistication of when to use measure spaces built on hyper-spherical, rather than hyper-cubic expansions. At least Math folks can tell what is efficient, for resolving a given target.

It is refreshing to see people are taking the need seriously, to address the Information Science/Information Technology gap in understanding. I shall pass your links on to my friend Leo KoGuan. I recently overheard him talking with someone from Templeton about funding research in this general direction. Then we saw an excellent lecture from former LIGO head Barry Barish. I'll be at GR21, but I won't be likely to get to the conference mentioned. However; it is really good to see the progress on this topic.

`I am very happy to see this Pierre. I have seen that the bulk of the computing community makes do with crude distance measures, when analyzing high-dimensional datasets, then uses a brute-force approximation. Worst; people in Computer Science seem to completely lack the sophistication of when to use measure spaces built on hyper-spherical, rather than hyper-cubic expansions. At least Math folks can tell what is efficient, for resolving a given target. It is refreshing to see people are taking the need seriously, to address the Information Science/Information Technology gap in understanding. I shall pass your links on to my friend Leo KoGuan. I recently overheard him talking with someone from Templeton about funding research in this general direction. Then we saw an excellent lecture from former LIGO head Barry Barish. I'll be at GR21, but I won't be likely to get to the conference mentioned. However; it is really good to see the progress on this topic.`