INNOVATION - AI Dynamics

ConvNets Translation-Invariance and Layer Equivariance Properties

By

–

12 November 2022 23h05

The output of a convnet is translation-invariant by design. Individual intermediate layers are equivariant. (Transformers may or may not be invariant/equivariant, btw.)

→ View original post on X — @pmddomingos

12 November 2022

Industrial IoT Priorities in Enterprise AI Strategy

By

@fogoros

–

12 November 2022 22h41

Thanks, for clarifying, sounds like Industrial IoT is at the bottom of of your priorities 🙂

→ View original post on X — @fogoros

12 November 2022

Tech Layoffs Drive Talent Toward National Security Sector

By

@bobgourley

–

12 November 2022 22h33

So sorry for all impacted of course. Hoping innovators will innovate in this time of stress. If you were laid off think of joining the national security sector, your nation needs you.

→ View original post on X — @bobgourley

12 November 2022

Global Online AI Event Sells Out with 6000+ Attendees

By

@fogoros

–

12 November 2022 22h19

Last chance. This global ONLINE event will be sold out. We expect over 6000+ registered attendees from over 125 countries. We only have a few sponsorships available.

→ View original post on X — @fogoros

12 November 2022

Creative AI as Companion to Human Creativity and Discovery

By

@emollick

–

12 November 2022 22h12

Creative AI is going to be an interesting companion to human creativity, helping find unexpected connections. For example, Metaphor uses predictive search to guess the links that might shed light on your question. The answers are uneven, but fascinating. https://
metaphor.systems

→ View original post on X — @emollick

12 November 2022

AI Texture Generator for Unity – Paid Tool Release

By

@alexjc

–

12 November 2022 22h03

AI Texture Generator for Unity (paid tool) https://
assetstore.unity.com/packages/tools
/ai/ai-texture-generator-234104
…

→ View original post on X — @alexjc

12 November 2022

Algorithm discovers specific symmetries from defined possibility space

By

@pmddomingos

–

12 November 2022 21h25

We tell them the space of possible symmetries (e.g., affine); the algorithm discovers which (e.g., translation, or some translations).

→ View original post on X — @pmddomingos

12 November 2022

Learning Symmetries: Discovering Constraints in Phenomenon Modeling

By

@pmddomingos

–

12 November 2022 21h23

The prior is that there's a space of symmetries the phenomenon being modeled may obey (e.g., affine), and the learning task is to discover which (e.g., only translations, or only some translations).

→ View original post on X — @pmddomingos

12 November 2022