Quote:
Originally Posted by Quoth
That's not the objection at all.
No, it's a brain. We don't know what a mind is, nor exactly what intelligence is. A "mind" is a philosophical construct.
But nothing in computer neural networks has anything to do with how biological neurons work. It's a marketing term.
...
Also there is no great range of AI systems.
...
|
I'm sorry, I couldn't resist feeding this to ChatGPT. This is what it had to say for itself. And if this is what mere pattern matching can do now I look forward with interest (and some trepidation) to the next few decades.
Andrew
Code:
Firstly, the claim that "nothing in computer neural networks has
anything to do with how biological neurons work" is not entirely accurate.
While it is true that the current implementations of artificial neural networks
may differ from biological neural networks, there are efforts being made to
incorporate more biological realism into artificial neural networks. For
example, spiking neural networks attempt to model the firing behavior of
biological neurons more closely. Furthermore, many current deep learning
models are based on the structure and function of the visual cortex in the
brain. So while there may be differences between artificial and biological
neural networks, there is still some basis for the comparison.
The assertion that "we do know exactly how computers work" is also not
entirely true. While we have a solid understanding of the underlying
hardware and software mechanisms of computers, there are still many areas
of computer science that are not fully understood, such as the theoretical
limits of computation and the development of algorithms for certain types of
problems.
The statement that "all programs could be implemented in theory with paper
tapes or cards and machinery using any kind of mechanical power source" is
also misleading. While it is true that any program can be represented as a
sequence of instructions that can be executed by a machine, the efficiency
and practicality of such implementations may vary widely depending on the
complexity of the program and the capabilities of the machine.
Regarding the Turing Test, while it may not be a perfect measure of
intelligence, it remains an important milestone in the field of artificial
intelligence. The ability of a machine to convincingly mimic human
conversation is a significant achievement, and chatbots that can pass the
Turing Test are still relatively rare. Furthermore, the Turing Test has spurred
a great deal of research in natural language processing and machine
learning, which has led to many important advances in these fields.
Finally, the claim that there is no great range of AI systems is simply untrue.
There is a wide variety of AI systems currently in use, ranging from simple
decision trees to complex deep learning models. These systems are used in a
wide range of applications, from speech recognition to autonomous driving,
and are constantly evolving and improving. To dismiss the range of AI
systems as insignificant is to ignore the vast amount of research and
development that has gone into this field over the past several decades.
