Reservoir Computing

Reservoir Computing

Reading Time: 1 minute

Reservoir Computing

The idea is commonly known as “reservoir computing” and came from attempts to develop computer networks modeled on the brain. It involves the idea that we can tap into the behaviour of physical systems – anything from a bucket of water to blobs of plastic laced with carbon nanotubes – in order to harness their natural computing power.

The basic idea is to stimulate a material in some way and learn to measure how this affects it. If you can work out how you get from the input stimulation to the output change, you will effectively have a calculation that you can then use as part of a range of computations. Unlike with traditional computer chips that depend on the position of electrons, the specific arrangement of the particles in the material isn’t important. Instead we just need to observe certain overall properties that let us measure the output change in the material.

Wow. I’d not heard of this before, but it seems pretty intriguing and I can see how something like this might work well with machine learning approaches. The trick, I suppose, is figuring out how to “train” the material, and that’s the part I don’t get here. I can see training a Deep Learning system by tuning the features, but how would one tune a bucket of water?

Thanks John Verdon and Mark Bruce.

Originally shared by John Verdon

Thanks Mark Bruce


  1. The most fundamental computation is just state change – anytime an object, system, molecule or atom changes it’s state, and that state change can be utilized/recorded, you have computation. This is why so many people believe that spacetime is fundamentally computational – because all we’re talking about are using the most basic state changes in a logical way.

    Eventually, all matter and energy can be made to do this for us, thus the idea of the universe ‘waking up’ as we program matter, and maybe even spacetime, itself.

  2. That’s a really amazing thought, Darius Gabriel Black. I’ve heard Steven Wolfram talk about the computational power of clouds and other natural systems, but I suppose I just chalked it up to some abstract idea rather than this very specific meaning.

    Very, very interesting.

  3. I like the pitr

  4. Wow! Gideon Rosenblatt I’d not heard of this before, either. Mind is boggling. State change as 0s and 1s.

  5. Very innovative approach to computing. Still it may be a long way to go.

  6. Gideon Rosenblatt reminds me of this:

    “Miniaturization was the big theme in the first age of computers: rising power, falling prices, computers for everybody. Theme of the Second Age now approaching: computing transcends computers. Information travels through a sea of anonymous, interchangeable computers like a breeze through tall grass. A dekstop computer is a scooped-out hole in the beach where information from the Cybersphere wells up like seawater.”


  7. Full of really interesting insights, Thomas Morffew. I like the cyberbodies idea.

    On a more practical note, this jumped out as very true:

    30. If you have three pet dogs, give them names. If you have 10,000 head of cattle, don’t bother. Nowadays the idea of giving a name to every file on your computer is ridiculous.

  8. Wow, the implications of this in the theory of quantum universe is enormous. Thanks

  9. Awesome. Yet another blurred boundary. Computing just an interpretation of state changes. Information just an interpretation of state of affairs. Have to digest that.

  10. Yeah, me too, Bernard Vatant. If this approach gets worked out, it would be revolutionary.

  11. So the illusion of time comes from the labeling sequence of fixed units emerging from its pattern.

  12. For Information About Latest Jobs and Help through Online Chat Visit –

Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.

Sign up here for the latest articles. You can opt out at any time.

Subscribe by email:

Or subscribe by RSS:

%d bloggers like this: