Slashdot Mirror

← Back to Stories (view on slashdot.org)

Overlaps Between Biological And Artificial Neural Networks?

Posted by Cliff on from the convergences-and-divergences dept.

snurfer asks: "I'm very interested in the overlap between biological and neural networks, but I don't know much about the research being done in these areas. Where do people think the next breakthrough in neural network-type computing is coming from? Is there any possibility that improved understanding of neural function and how the biological brain solves problems and learns/remembers might flow into the next generation of software? I guess just in general, are the two research areas still borrowing from each other, or have they diverged too far to be of mutual benefit?"

3 of 8 comments (clear)

  1. The facts by yamla · · Score: 3
    There is almost no overlap between biological and artificial neural nets. In fact, it was somewhat misleading of the early AI researchers to label them 'neural nets' because even back then, we knew that a single neuron was far more complex than the artificial kind.

    Artificial neural nets are really great in a very small number of applications. They can particularly show good results for pattern recognition and can help you identify important criteria to solve a problem when you really have no other ideas on how to solve it.

    But the field of AI research all but abandoned neural nets in the 1980s. They tend not to scale up well, they are simply useless for a large number of AI problems, and studying them tells you nothing about the human brain.

    --

    Oceania has always been at war with Eastasia.
    1. Re:The facts by yamla · · Score: 2
      There were indeed problems like this in the 80s. Many of them were solved and many more advances were made, including better backprop algorithms and all kinds of other things.

      However, neural nets were at one point considered almost the 'holy grail' of artificial intelligence. We now know that neural nets are not and likely never will be. They are very good at solving a small range of problems but are totally unsuitable for many many problems.

      Furthermore, the tuning that has been done to neural net algorithms generally makes them less like real human neurons, rather than more like them.

      Many undergrads learn about neural nets and get all excited about the possibilities. After only a while of studying, this excitement typically ends. There is very little research still being done on neural nets (compared to the late 70s and early 80s) at the post-graduate level.

      --

      Oceania has always been at war with Eastasia.
  2. The little bit of information I can provide... by dougqh · · Score: 3

    Artificial neural networks and actual neural networks are quite different, but neural nets have been used in a limited capacity to help explain some neurological disorders. These range from phantom limbs, schizophrenia, Alzheimer's, and more. If you really wish to learn more about the subject I would highly recommend reading _The Mind within the Net_ by Manfred Spitzer published by MIT Press. It is quite a good beginning explaination of how artificial neural networks can contribute to understanding their biological counterparts. That is about all the information I can provide hopefully it will be of some use to you.