Photo by Ryan Stone on Unsplash

There’s a curiously interesting thing about reading words on a page. The words are static and unlike real things, how words appear does not significantly change based on your physical interaction. But their meaning changes with mental interaction.

It can be argued that the ambiguity found in natural language leads to different interpretations and hence leads to creativity.

But not only is natural language ambiguous, but it also leaves out a lot of contexts. This context in fact may not even overlap between writer and reader.

Even words that are written by the person who is also the reader can…

Photo by Cas Holmes on Unsplash

The only thing that remains constant is change. If you think about it, what is constant is relative to time. Furthermore, what is constant is relative to what is moving. For physicists, something that is constant (i.e invariant) describes symmetry.

A symmetry is furthermore defined as a *change* in a reference frame. In other words, you can’t define a constant unless there is something that changes.

What is constant is what is perceived to not change. It is the very definition of an abstraction. We are able to perceive the world because we abstract the world into things that don’t…

Photo by Alonso Reyes on Unsplash

Systematic thinking and general intelligence are two different things. We build models of general intelligence that employ systematic thinking. However, this should not imply that general intelligence is built out of systematic thinking.

Logic and probability are examples of systematic thinking. The naive approach to creating models of general intelligence is to assume that they need to be constructed of systematic methods.

So there is this tunnel vision among GOFAI folks and Bayesians that the tools that their epistemological tools are the same tools that biological brains employ. This is clearly misguided.

It is as misguided as claiming that the…

Photo by Dragos Gontariu on Unsplash

The curse of knowledge is that experts become unconscious of their current knowledge and forget how they arrived at that knowledge.

Photo by Toa Heftiba on Unsplash

The “Reward is Enough” paper offers a questionable framing as to how AGI is achieved. The argument of this paper is that to achieve AGI all that is enough is a reward function. All supplementary skills are eventually learned to achieve the reward. The major flaw of the ‘Reward is Enough’ paper is that the authors aren’t able to disentangle the self-referential nature of the problem. The framing appears to be tautological.

Then there’s the question about reward. Where is that coming from? It’s the same fallacy so pervasive in science. That is the belief in the existence of a…

Photo by JESHOOTS.COM on Unsplash

The embrace of continuous variables in our formalization of nature implies infinite information. It is analogous to the notion of aether, that there is always some medium that is the substrate for the propagation of discrete particles.

Continuiousness is an emergent property of the measure of discrete interactions at different scales. There is no aether and there are no infinite precision variables.

When we examine chemistry, all the energy jumps between the electron shells of an atomic are discrete. When we examine biology, all energy is released in discrete form in the breaking of ATP.

When examining the brain, we…

Photo by Hannah Wright on Unsplash

The term linear in the traditions of mathematical programming and hence machine learning doesn’t have the same meaning as linear in the tradition of physics. So when ML folks speak of non-linearity, it is not the same as non-linear that physicists speak of. I read this latest article and it was obviously apparent. “They’re “linear” because the only allowable power is exactly 1 and graphs of solutions to the equations form planes.”…

Dynamical equations in physics usually have the power of 2. A non-linear equation in physics is one that typically does not have a closed-form analytic solution. …

This is a demonstration of how the brain’s consensus mechanism works:

Permit me to explain why your brain is flipping its interpretation of the image. For starters, human vision acts very similarly to touch.

When your eyes look at an image, it is actually rapidly moving around and ‘feeling’ the image. The part of the retina, known as the fovea, can see color, and high resolution is just a small fraction of what you see in front of you. However, even if your eyes are moving, you see a stable image in front of you. …

Photo by Mika Baumeister on Unsplash

Thrilled today to have anticipated around two years prior a paper that DeepMind just released. This is validation that my approach to general intelligence. Here’s the said paper:

Quoted from the paper “Our definition of a symbol draws on the work of the philosopher Charles Sanders Peirce. Peirce outlined three categories of relation — icons, indices, and symbols — whose definitions illuminate the role of convention in establishing meaning.” The authors conclude that “The views we’ve presented here seem to run counter to the past and current AI zeitgeist surrounding symbols, which emphasizes rigid mechanisms and particular representational forms.”


Photo by Loic Leray on Unsplash

Nice to discover Judea Pearl ask a fundamental question. What’s an ‘inductive bias’? Pearl tweets:

“Help! What precisely is “inductive bias”? Some ML researchers are in the opinion that the machine learning category of ‘inductive biases’ can allow us to build a causal understanding of the world. My Ladder of Causation says: ‘This is mathematically impossible’. Who is right?”

A crucial step on the road towards AGI is a richer vocabulary for reasoning about inductive biases. Pearl explores the apparent impedance mismatch between inductive biases and causal reasoning. …

Carlos E. Perez

Author of Artificial Intuition and the Deep Learning Playbook —

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store