Follow project on Twitter
NederlandsEnglish

2.2. Artificial / Deep-learning Neural Networks

First of all, neurons are not essential to intelligence, in the same way as feathers and flapping wings are not essential to aviation. So, neurons are not the source of intelligence.

Lacking an operating system with designed functions, Artificial Neural Networks (ANN) are limited to perform pattern recognition. And Deep-learning Neural Networks (DNN) are limited to perform trained tasks, based on pattern recognition.

ANNs are engineered to store an average pattern, based on a training set of patterns. Humans have to select the patterns of the training set. This selection process requires natural intelligence. ANNs are not based on natural intelligence. So, this selection process can only be done by humans. Humans are therefore the only intelligent factor in pattern recognition. Not the ANN.

The word “learning” is therefore a misfit term when used in regard to an ANN. To illustrate:

We don't have to feed a child thousands of pictures of a cat before a child is able to recognize a cat. One example of a cat may be sufficient for a child to distinguish this type of animal from other types of animal. At the moment the child sees another cat, it will point to the animal and ask “Cat?”, in order to get a confirmation that it has learned to distinguish this type of animal from other types of animal correctly.

My father taught me: “Don't become a monkey that learns a trick”. DNNs are engineered to perform a trick, based on pattern recognition. Humans design algorithms that describe the essence of the task. After a lot of training runs, the DNN has mastered to perform that trick, without understanding the essence of the task. Designing the algorithms, requires natural intelligence. DNNs are not based on natural intelligence. So, the algorithms can only be designed by humans. Humans are therefore the only intelligent factor in performing the trained trick of a DNN. Not the DNN itself.

The word “learning” is therefore also a misfit term in regard to a DNN. To illustrate:

We don’t need to play a game thousands of times, before a child is able to play this game. Explaining the rules of the game may be sufficient for a child to play that game, while the rules of a game can't be explained to a DNN.


The only way to improve pattern recognition: To identify individual parts of each object, like the left ear of a cat, its right ear, its nose, its whiskers, its mouth, its tail, each eye, each leg, and so on. Initially, humans have to perform this task. I am not sure if it can be automated later on.