Actions
Forum Thread Details
  • State Not Answered
  • Replies 2 replies
  • Subscribers 8 subscribers
  • Views 702 views
  • Users 0 members are here
Related

Neuromophic Computing

clem57

The brain on "Chips"

Neuromorphic computing is an emerging technology that has actually been emerging for quite some time. It was first proposed in the 1980s by Carver Mead to take advantage of some of the technologies emerging in very large-scale integration (VLSI). The idea was to put a large array of analog circuits on a single chip where all of the individual analog blocks were designed to leverage our knowledge of:

  1. Biologically based neural architectures in living nervous systems.
  2. New machine learning algorithms.
  3. Physical microelectronics.

One of the driving forces in this computing domain is because the end is in sight for the dramatic exponential growth of single processor von Neuman computer architectures. (Of course, it is the driving force for parallelism, quantum computing, etc. Who doesn't stay up nights worrying about the day when we can't compute any faster?!)

 

What do you know about this topic?

  • 0

    An interesting article based on the above and leading into Ann: Analog Neural Network Model

     

    Probably the largest hurdle is not about what we can build, but identifying novel, efficient computation in neurobiology and employing these techniques in engineering applications. This question is the fundamental open question for neuromorphic engineering as well as neuroscience. Given that the neuromorphic engineering building blocks also can be accurate models for neurobiological behavior, these questions are directly related. We painted a picture of the potential computational models arising from neuro-modeling, including their potential computational efficiency; we expect these models are just a start to what is possible. We expect neuroscientists are bound to make more fundamental discoveries about the nature of the biological computation, discoveries that most likely will further improve the computational efficiency and other metrics of these systems.

    From: https://www.frontiersin.org/articles/10.3389/fnins.2013.00118/full

    Clem

  • 0

    I remember when this idea came out and at the time, technology just was not up to the task, nor was there a large enough demand to make developing the technology.

     

    In many ways, the great advances in digital signal processing has overtaken the need to do this project in analog.

     

    Current AI technology implements a fair amount of the idea in various ways.

     

    DAB