πŸ“– Ebook: Insights from the brain, the road towards Machine Intelligence

After a (longer-than-expected) fantastic & intense journey, I am very glad to share my free illustrated ebook about insights from the brain that are currently – or could be soon – used in neuroscience-grounded AI approaches.

I think it could help people with a computer background to get onboard with HTM and other bio-inspired ideas.

I already talked about this ebook in some posts on this forum. In fact, I structured and refined some of its content by reading many discussions here. Thanks you all for this. I am also very grateful to @Bitking, @Casey and @Falco who dedicated a lot of time to help me with review and proofreading.

You can download it here:

Ebook foreword

This illustrated ebook formulates my own perspective of some key neuroscience knowledge that is currently (or could be soon) used in neuroscience-grounded AI efforts, following my deep conviction that the road towards machine intelligence is inseparable from a mixed AI & neuroscience approach. It builds upon my difficult but rewarding experience of navigating through neuroscience papers with a datascientist perspective during several months.

The first part – the longest – is dedicated to biological intelligence. It begins with the fundamental role of physical actions into the gradual emergence of high-level cognitive abilities through evolution. Then, the level of sophistication of the described neural machinery will appear unrivaled compared to today’s deep learning artificial networks. I highlight the neocortex, a highly-researched brain structure that currently inspires many AI & neuroscience researchers because of its central role in human intelligence. In order to keep this document short, I had to make choices. One of those choices was to skip the focus on probably underrated subcortical sensorimotor circuits, and on two other popular brain structures in the AI community: the basal ganglia and the hippocampus. I keep those topics for another time.

The second part deals with biologically-inspired AI, starting with the modelling of more realistic neurons, architectures and learning rules into artificial networks. It subsequently continues with the transition from abstract artificial networks to artificial agents learning lifelong by interacting with their environment through their own perspective.

The primary target audience is the classical AI community interested to get insights from brain mechanisms. Also, curious neuroscientists who would like to keep up with neuroscience-grounded AI initiatives are invited to skip to the second part.

I already reached a personal goal with the completion of this ebook. My second goal will be reached if some AI & neuroscience enthusiasts actually benefit from this reading.

I would be happy to read your comments, answer your questions, correct the errors that you may have spotted, add key missing elements to the document, or just discuss machine intelligence & neuroscience with you.

Matthieu Thiboust


What a wonderful book! I’ve just started to read it after skimming it… Wow. This is a huge effort and it is really well done!!


The time is now! Thank you Mattheiu! I’m excited to start reading!!!


Great job, @mthiboust.

A great source of concise information. And nicely presented.

Thank you!


@mthiboust thanks for sharing your book. I like to read it …


@mthiboust - Wow fantastic job, that book is amazing you need to publish that. Gonna take some time to unpack all the information you presented in it.


@mthiboust made this public while I was away from the forum on personal business, but I just want to say how outstanding this resource is. I really don’t know of a better primer into neuroscience for AI like this one. He has been working on it for a very long time, and it shows. The graphics are outstanding, even those he has gathered from other resources. He puts together a cohesive narrative about intelligence in brains and suggests where we should continue looking for clues. Such a good job! : :clap::clap::clap::clap::clap:


Just WOW!!!


I’ll post a link to the archive video after the live-stream.

1 Like

Impressive work, Matthieu :star_struck:

1 Like


Thanks for the ebook. The graphical illustration made it so much easier to understand interactions between different layers for me.


it is good you decided to use Machine intelligence, rather than AI or AGI

1 Like

An important paper that shows the grounding of semantics in the sensory areas:


It will be nice if you include in a single place all the stats about the brain … count of neurons,mcols, cc, … sizes… layers nomenclature… etc.
Like HTM cheatsheet but just the numbers :wink:

I’ve been lacking bio details, learning some stuff :slight_smile: thanks … on page 64
those convoluted names are killing me

@mraptor: If you want some numbers about the cortical inhibitory interneurons described on page 64, have a look at this page: https://portal.brain-map.org/explore/models/mv1-all-layers

They modeled a piece of mouse V1 cortex in great details and you have the proportion of those neurons by and between layers:



Wow, thanks for this, something to enjoy during lockdown :slight_smile:


I wanted to see just the page heading text with page numbers, so I created a plain text file with just that information. I find these headings make an interesting, if terse, summary and index of the topics.

Biological intelligence

Brains and cognitive abilities

  1. The primary function of a brain is not to think but to efficiently control complex behavior 10
    The brain is the central part of a bidirectional signaling system that generate complex behavior 11
    The control of the different behaviors is distributed over a collection of brain substructures 12
    Perception and cognition gradually emerged throughout evolution to support increasingly complex behaviors 13
  2. This control is supported by abilities that were progressively acquired and refined through evolution
    Brains of current living creatures result from an evolutionary process of 700 million of years 15
    The neocortex is a major brain innovation along the vertebrate phylogenetic branch 16
    Evolution plays with the brain developmental recipe, not directly with mature brain characteristics 17

In case anyone would like to see the complete result, I put it here: