January 6, 2018
There are many criticisms that the biological brain or biological neural networks operate in a completely different way from the currently popular computer neural networks. Those comments are used by various specialists, both from biologists, neurophysiologists and from specialists in computer science and machine learning, but at the same time there are very few specific comments and suggestions. In this article, we will try to analyze this problem and identify particular differences between the work of a biological and a computer neural network, and propose ways to improve computer neural networks that will bring their work closer to a biological analogue.
First, I want to explain why, in my opinion, in the matter of creating a strong artificial intelligence, everything is still so sad, despite the tremendous advances in computer science and knowledge about the biological brain. First of all, this is due to the large ideological gap between these two pillars of science. Computer science requires a certain schematic simplicity, rigor and conciseness in the description of systems, a certain systematic approach, in discarding unnecessary and clear structuring sufficient for design in the program code. In biology, the details of the description of the observed systems dominate; nothing can be discarded or ignored from observations. All observable facts should be included in the systems described. Therefore, it is difficult for biologists to apply a systematic approach to their vast knowledge to create brain algorithms. After all, in order to create the construct of the aircraft, it took a lot to revise and discard from the image of a bird.
On the other hand, it is easy to understand scientists and engineers who, when immersed in the study of computer neural networks, from the description of the principles of the brain work, are content with a short paragraph of text about a neuron that, using synapses on dendrites, “listens” to other neurons and transmits the result of summation calculations over the layer via a single axon further, without applying any critical assessment to this knowledge. Even neuroscientists use the formal McCulloch-Pitts neuron to describe the principles of a biological neuron, but they do it for a different reason, because there are no worthy alternatives, there is no clear description in biology of what a neuron does, what logic it performs, despite extensive knowledge about it.
If someone tries to reengineer the work of the brain, then he will come across a whole layer of accumulated conflicting knowledge, which is actually not enough for even a biologist’s life to understand, let alone a systems engineer who is accustomed to a more different form of knowledge. It is possible to work with such a volume of information only through the prism of some general theory of the brain, which does not yet exist.
Humanity possesses technologies of colossal computing power and a gigantic amount of knowledge about the brain, but cannot obtain a synthesis of these things. Let’s try to solve this problem and erase this knowledge boundary.