Explainable AI
from first principles

Em. prof. Bart ter Haar Romeny
Eindhoven University of Technology
The Netherlands

At SSIMA 2022, Oradea, Romania, 05-09-2022

Easy Deep Learning
- An introduction

Explainable AI from First Principles

Deep Learning for doctors & neuroscientists

The Retina and Visual System

Lectures given at DeepLearn Spring 2022, 5th International School on Deep Learning. Guimaraes, Portugal, 18-22 April:

A highly interactive tutorial

This series of lectures is almost completely presented with life coding examples in Mathematica (Wolfram Inc.). The course notes are all computational essays. Attendees will discover that this is an ideal environment to study deep learning, and combine it with both deep understanding of - and play interactively with - the underlying mathematics.

And yes, we will do mathematics, and physics, and all will be explained visually and intuitively. The approach is focused on geometric deep learning, and deriving solid insights by exploiting first principles.

I also discuss modern insights in visual perception, the retinal connectome, and what seems to happen in the many layers of the visual system in the cortex.

TED/x lecture Eindhoven, 30-01-2018

All the Mathematica notebooks will be made available on this website, so all that is explained during the lectures can be studied at ease later on by doing it.

The course is suitable for beginners and experts in Deep Learning programming.

The lectures are based on the following books, each completely written in Mathematica. This means that the text is interactive, all topics that are discussed come with full code, i.e. free downloadable Mathematica notebooks.

Romeny, Bart M. Haar. Front-end vision and multi-scale image analysis: multi-scale computer vision theory and applications, written in mathematica. Vol. 27. Springer Science & Business Media, 2008.

Download the book