Uke 39 - Annenordens intelligens


Da jeg leste Carver Mead: "How we created Neuromorphic Engineering", gjorde jeg meg noen refleksjoner:


I "The ‘prediction imperative’ as the basis for self-awareness" av Rodolfo R. Llinás og Sisir Roy :

"…global brain function is geared towards the implementation of intelligent motricity. Motricity is the only possible external manifestation of nervous system function (other than endocrine and exocrine secretion and the control of  vascular tone).

The intelligence component of motricity requires, for its successful wheeling, a prediction imperative to approximate the consequences of the impending motion.

We address how such predictive function may originate from the dynamic properties of neuronal networks."

 In Carver Mead: "How we created Neuromorphic Engineering", Nature Electronics, 2020-07-21:

"We started with sensory systems — vision and hearing — because they are the primary source of information for the brains of a wide variety of animals, and have been studied extensively by neurobiologists. They have the additional advantage that they give live information from the real world, as opposed to dead bits stored in computer memory. The retina, in particular, is an extension of the brain into the eyeball. Its function is to extract information from the visual scene that is useful to the animal, and pass this compressed information to higher levels in an efficiently encoded form."

…

"At each higher level, the system extracts information from its inputs and builds a more sophisticated model of its world. In current commercial ‘neural networks’, the learning process is carried out primarily by digital algorithms on stored data, and the corrections to the model at each level are done by back-propagation of errors from higher levels. Instead of predicting the future input as it rolls by, most learning is supervised: that is, the output is told what it should predict, and the model is punished if it gets the wrong answer."


Copied from: Carver Mead: How we created Neuromorphic Engineering, Nature Electronics, 2020-07-21 (ReadCube)

Refleksjoner:

sitater:

“Der Mensch kann tun was er will; er kann aber nicht wollen was er will.”
― Arthur Schopenhauer  (1788-1860)


"Det er to måter å bli lurt på. Den ene er å tro på det som ikke er sant. Den andre er å nekte å  tro på det som  er sant"
—Søren Kierkegaard (1813-1855)


“The first principle is that you must not fool yourself and you are the easiest person to fool.”
― Richard P. Feynman  (1918-1988)


"The better we get at getting better, the faster we will get better."

"A key to the long-term vitality of an organization —
to get better and better at improving itself."

"The key thing about all the world's big problems is that they have to be dealt with collectively. If we don't get collectively smarter, we're doomed."
― Douglas Engelbart (1925-2013)


"The world, as we perceive it, is our own invention"

"First-order cybernetics is the science of observed systems; Second-order cybernetics is the science of observing systems."
— Heinz von Foerster (1911-2002)


“That which we call thinking is the evolutionary internalization of movement.”

"Basically there are two types of animals: animals, and animals that have no brains; they are called plants. They don't need a nervous system because they don't move actively, they don't pull up their roots and run in a forest fire! Anything that moves actively requires a nervous system; otherwise it would come to a quick death."

"We assume that we have free will and that we make decisions, but we don't. Neurons do. We decide that this sum total driving us is a decision we have made for ourselves. But it is not."

—Rodolfo Llinás


…