Article  A new approach to computation reimagines artificial intelligence

#1
C C Offline
https://www.quantamagazine.org/a-new-app...-20230413/

INTRO: Despite the wild success of ChatGPT and other large language models, the artificial neural networks (ANNs) that underpin these systems might be on the wrong track.

For one, ANNs are “super power-hungry,” said Cornelia Fermüller, a computer scientist at the University of Maryland. “And the other issue is [their] lack of transparency.” Such systems are so complicated that no one truly understands what they’re doing, or why they work so well. This, in turn, makes it almost impossible to get them to reason by analogy, which is what humans do — using symbols for objects, ideas and the relationships between them.

Such shortcomings likely stem from the current structure of ANNs and their building blocks: individual artificial neurons. Each neuron receives inputs, performs computations and produces outputs. Modern ANNs are elaborate networks of these computational units, trained to do specific tasks.

Yet the limitations of ANNs have long been obvious. Consider, for example, an ANN that tells circles and squares apart. One way to do it is to have two neurons in its output layer, one that indicates a circle and one that indicates a square. If you want your ANN to also discern the shape’s color — blue or red — you’ll need four output neurons: one each for blue circle, blue square, red circle and red square. More features mean even more neurons.

This can’t be how our brains perceive the natural world, with all its variations. “You have to propose that, well, you have a neuron for all combinations,” said Bruno Olshausen, a neuroscientist at the University of California, Berkeley. “So, you’d have in your brain, [say,] a purple Volkswagen detector.”

Instead, Olshausen and others argue that information in the brain is represented by the activity of numerous neurons. So the perception of a purple Volkswagen is not encoded as a single neuron’s actions, but as those of thousands of neurons. The same set of neurons, firing differently, could represent an entirely different concept (a pink Cadillac, perhaps).

This is the starting point for a radically different approach to computation known as hyperdimensional computing. The key is that each piece of information, such as the notion of a car, or its make, model or color, or all of it together, is represented as a single entity: a hyperdimensional vector.

A vector is simply an ordered array of numbers. A 3D vector, for example, comprises three numbers: the x, y and z coordinates of a point in 3D space. A hyperdimensional vector, or hypervector, could be an array of 10,000 numbers, say, representing a point in 10,000-dimensional space. These mathematical objects and the algebra to manipulate them are flexible and powerful enough to take modern computing beyond some of its current limitations and foster a new approach to artificial intelligence.

“This is the thing that I’ve been most excited about, practically in my entire career,” Olshausen said. To him and many others, hyperdimensional computing promises a new world in which computing is efficient and robust, and machine-made decisions are entirely transparent... (MORE - details)
Reply
#2
Kornee Offline
The to me amusing aspect to all this is the incredible sophistication arrived at after prodigious collective efforts of many highly trained researchers, is blithely assumed to be completely compatible with blind evolution of animal brains utilizing even more advanced 'algorithmic strategies'.
Actually even that of insects and such. Like in some David Attenborough documentaries where e.g. certain species of spider employ amazingly complex strategies.
Yet have 'brains' many orders of magnitude smaller than those of dumb as it gets grass munching cows. Makes some stop and think.
Reply


Possibly Related Threads…
Thread Author Replies Views Last Post
  Quotes about Artificial Intelligence Magical Realist 29 1,299 Jan 3, 2024 10:25 AM
Last Post: stryder
  Article Artificial intelligence: Four debates to expect in 2024 C C 0 87 Jan 3, 2024 02:01 AM
Last Post: C C
  Article "Schrödinger’s cat" code makes for better qubits in quantum computation C C 0 108 Jun 8, 2023 07:15 PM
Last Post: C C
  Article Artificial intelligence finds the first stars were not alone C C 0 99 Mar 27, 2023 07:14 PM
Last Post: C C
  The danger of advanced artificial intelligence controlling its own feedback C C 0 185 Oct 25, 2022 08:21 PM
Last Post: C C
  Approach to demystify black box AI not ready for prime time C C 0 186 Oct 11, 2022 05:54 PM
Last Post: C C
  How artificial intelligence can explain its decisions C C 0 163 Sep 3, 2022 10:37 PM
Last Post: C C
  Machine learning reimagines the building blocks of computing C C 0 118 Mar 16, 2022 05:18 PM
Last Post: C C
  Will transformers take over artificial intelligence? C C 0 117 Mar 11, 2022 07:24 PM
Last Post: C C
  Consciousness in humans, animals and artificial intelligence C C 0 135 Dec 21, 2021 09:41 PM
Last Post: C C



Users browsing this thread: 1 Guest(s)