The experimental results from neurobiology have lead to the investigation of a third generation of neural network models which …

Found in Translation
Found in Translation
Whereas perfect algorithms (or working rules) were available for the performance of the elementary arithmetical and logical operations, … no such algorithms were in existence for translation
Moreover, whereas the notion of a “correct” computation is unproblematic … the notion of a “good” translation is ridden with problems
Bar-Hillel 1962
Julia and John are talking about the following article:
Machine translation


In this post the dialogue is realised by an interaction of virtual characters, for more information please check the page “Virtual characters“

Julia
I might have a good analogy!

John
Ok, let’s hear it then … 😊

Julia
Perhaps we can compare it to machine translation 😊

John
Interesting, in what way?

Julia
I read somewhere that the classical approach to automating translation was to analyze every sentence according to its grammatical structure “Rule-based machine translation“

Julia
Find the subject, object, verb, and everything else, with their gender, number, aspect, tense, etc.

Julia
and then the translation program replaces them with their equivalent in the target language, keeping their relations the same.

John
And we can compare that to the explicit programming of the laws of thought approach, right?

Julia
Indeed! But the alternative is to simply use an enormous amount of data, of translated samples, to generalize and learn through statistics

John
Which is like the implicit approach? Where the rules don’t matter as long as it comes out right?

Julia
Yes, broadly. The analogy is not perfect, but I think it might help.

John
I guess most people are familiar with automatic translation nowadays

Julia
That’s also why I picked this particular example

John
But which approach do the popular free on-line tools use?

Julia
To the best of my knowledge, they all use the statistical approach

John

Julia
This has been very interesting and instructive, thanks again for the opportunity of collaborating on this!

John

Julia
I look forward to doing this again sometime

John
Absolutely, I’ll keep you posted!
… Continue reading our conversations that are posted every Monday …
Related post
Total posts on the argument
All aboard the Spike Train!
The Network is the Message
A continued stimulus, such as a state of tension, a light or a sound, produces a continued passage of sensory impulses to the central nervous system.
I’m in your brain, releasing your transmitters
The mechanism of action of nerve stimulation is unknown… it is possible that substances are formed under the influence of nerve stimulation
Come in Neuron: do you copy?
If we liken the nervous currents to electric currents, we can compare the nervous system below the hemispheres to a direct circuit from sense-organ to muscle
Zap goes the Neuron
If I do not greatly deceive myself, I have succeeded in realizing… the hundred years’ dream of physicists and physiologists, to wit, the identity of the nervous principle with electricity
Today one Neuron, tomorrow the Brain!
The Navy said the perceptron would be the first non-living mechanism capable of receiving, recognizing and identifying its surroundings without any human training or control
Do Neurons Count?
Neural computers do not execute typical machine instructions of digital computers unless they are made to emulate the behavior of physical neural networks
Recent Comments