Gabriele Scheler – Medium

Gabriele Scheler

Breadth-First Selection for Matching Inputs

This is an interesting piece that came out the other day. It seems to underscore an idea that we published in 2025 and that further…

Oct 31

Breadth-First Selection for Matching Inputs

Oct 31

Models away from data

A foundation model uses datasets to output predictions given inputs, whereas a world model describes underlying structure implicit in that…

Oct 12

Models away from data

Oct 12

Mechanical Transmission

An important new concept for computational neuroscience is mechanical transmission. It would incidentally show why neuromorphics are a side…

Oct 2

Mechanical Transmission

Oct 2

Q&A AI and Brain Theory: Dec 18th (online) — new edition

How did modern AI start, how was it developed? What are neural networks, what happened to symbolic reasoning and why did the perceptron…

Sep 8

Q&A AI and Brain Theory: Dec 18th (online) — new edition

Sep 8

Comments on the debate on AI/LLMs — with a reference to the new tool braincentric.ai

Here are a few remarks which I collected over the last month or so. All refer to problems in building braincentric.ai.

Jul 28

Comments on the debate on AI/LLMs — with a reference to the new tool braincentric.ai

Jul 28

Real Brains are different: The role of E-I and I-I networks

While many ideas exist on building artificial or in more modern terminology, “digital” brains — including neural networks, neurosymbolic…

Jul 15

Real Brains are different: The role of E-I and I-I networks

Jul 15

Memory and prediction

Most neural network models have the property that they store incoming information over time sequentially, and then use additional…

Jun 23

Erich Correns: Ludwig II arriving at Berg on Lake Starnberg

Jun 23

Trivial Pursuit

Current AI models solve the knowledge bottleneck. They implicitly show that intelligence requires knowledge. While IQ can be measured as an…

Mar 19

Trivial Pursuit

Mar 19

AI characterizes novel non-standard memory model

This is about a new model which uses symbolic abstraction and high mutual information neurons. In this study, the authors present a model…

Feb 24

Feb 24

Physics-based AI

Why are we not interested in physics-based ANNs? Would that not be a smart way to endow a model with prior knowledge?

Feb 8

Physics-based AI

Feb 8

Gabriele Scheler

Gabriele Scheler

Computer scientist, logician, AI researcher and neuroscientist, supporting a non-profit foundation, Carl Correns Foundation for Mathematical Biology.

Following

Help

Status

About

Careers

Press

Blog

Privacy

Rules

Terms

Text to speech