^TagArtificial neural networks vs. neurons

black metal spiral staircase in grayscale photography

^{Type
post

Author
Eric Holloway
Date
August 8, 2022

Categorized
Artificial Intelligence, Philosophy of Mind, Programming

Tagged
AND function, Artificial neural networks (ANNs), Artificial neural networks vs. neurons, Decision regions in neural networks, Decision surfaces in neural networks, Featured, Incremental learning in neural networks, Logic functions, Logic functions and neural networks, Mind vs. brain, Mind vs. neural networks, Multilayer perceptrons, Neural networks' limitations, Neurons, Neurons vs. artificial neural networks, Perceptrons, Python (program), Truth tables, XOR function}

How AI Neural Networks Show That the Mind Is Not the Brain

_{A series of simple diagrams shows that, while AI learns faster than the human brain, the human mind tackles problems that stump AI} _{Eric Holloway

August 8, 2022

11

Artificial Intelligence, Philosophy of Mind, Programming}

Recently, I’ve been arguing (here and here, for example) that we can use artificial neural networks (ANNs) to prove that the mind is not the brain. To recap, here is the logic of my argument: Premise A: neural networks can learn better than the brainPremise B: the human mind can learn better than a neural networkConclusion: the human mind can learn better than the brain, therefore it is not the brain This means if we can conclusively show the human mind can learn better than a neural network, then the mind is not the brain. For Premise A, I’ve argued that the differentiable neural network is a superior learning model compared to the brain neuron’s “all or nothing principle”. The Read More ›

3D illustration, embossed mesh representing internet connections, cloud computing and neural network.

^{Type
post

Author
Eric Holloway
Date
August 2, 2022

Categorized
Artificial Intelligence, Neuroscience

Tagged
Artificial neural networks vs. neurons, Backpropagation algorithm, Featured, Marvin Minsky and perceptrons, Neurons (all or nothing principle), Perceptrons (all or nothing principle), Perceptrons' limitations, XOR function}

Can Computer Neural Networks Learn Better Than Human Neurons?

_{They can and do; when artificial intelligence programmers stopped trying to copy the human neuron, they made much better progress} _{Eric Holloway

August 2, 2022

5

Artificial Intelligence, Neuroscience}

Neural networks are all the rage in computing these days. Many engineers think that, with enough computer power and fancy tweaks, they will become as smart as people. Recent successes playing games and predicting protein folds pour gasoline on the AI fire. We could be on the edge of the mystical Singularity, when humans and computers will merge and we become immortal gods. Or not. Let’s wind the clock back to the beginning of neural networks. In computer science terms, they are actually a very old technology. The earliest version, called a perceptron, (a single-layer neural network) was invented in the 1960s, inspired by McCulloch and Pitt’s early model of brain neurons. But, the perceptron was ignored for decades because Read More ›

^{Type
post

Author
Eric Holloway
Date
July 24, 2022

Categorized
Artificial Intelligence, Neuroscience, Philosophy of Mind, Programming

Tagged
Artificial neural networks (ANNs), Artificial neural networks vs. neurons, Featured, Hodgkin-Huxley model of a neuron, McCulloch–Pitts model of neurons, Mind vs. brain, Mind vs. neural networks, Neurons vs. artificial neural networks, Perceptrons and error backpropagation, Society of Mind (book 1987)}

Artificial neural networks can show that the mind isn’t the brain

_{Because artificial neural networks are a better version of the brain, whatever neural networks cannot do, the brain cannot do.} _{Eric Holloway

July 24, 2022

4

Artificial Intelligence, Neuroscience, Philosophy of Mind, Programming}

What is the human mind? AI pioneer Marvin Minsky (1927–2016) said in 1987 that essentially “Minds are what brains do.” That is, the mind is the result of electrical waves cycling through the brain, as neurons spike and synapses transmit signals. But is that true? Can we test this idea? We can indeed, using artificial neural networks. One of the most popular approaches to artificial intelligence is artificial neural networks. These networks, inspired by an early model of how neurons fire (the McCulloch–Pitts model), consist of nodes, where each node is similar to a neuron. A node receives signals and then sends them to its linked nodes based on an activation function. There are, of course, differences between neural networks Read More ›