, , ,


A new type of neural network made with memristors can dramatically improve the efficiency of teaching machines to think like humans. The network, called a reservoir computing system, could predict words before they are said during conversation, and help predict future outcomes based on the present.

Memristors are a special type of resistive device that can both perform logic and store data and require less space and can be integrated more easily into existing silicon-based electronics. This contrasts with typical computer systems, where processors perform logic separate from memory modules.

Reservoir computing systems built with memristors, can skip most of the expensive training process and still provide the network the capability to remember. This is because the most critical component of the system – the reservoir – does not require training.

Who will your (future) automatic car decide to kill? [What does Jesus have to do with it?!?]

When a set of data is inputted into the reservoir, the reservoir identifies important time-related features of the data, and hands it off in a simpler format to a second network. This second network then only needs training like simpler neural networks, changing weights of the features and outputs that the first network passed on until it achieves an acceptable level of error.

Reservoir computing systems are especially adept at handling data that varies with time, like a stream of data or words, or a function depending on past results. “We can make predictions on natural spoken language, so you don’t even have to say the full word […] We could actually predict what you plan to say next”, claim the scientists. “It could also predict and generate an output signal even if the input stopped” researchers explained. (1)

How to Develop a Chess Program for Dummies 3

We like predicting.

But we are not who we are because we predict.

But because we do not.

We like understanding.

But we are not who we are because we understand.

But because we do not.

We believe that predicting based on data means something.

But it does not.

Humans used to be wise.

Computers speaking like humans? Irrelevant.

And then they replaced wisdom with knowledge.

Humans used to have knowledge.

And then they replaced knowledge with data.

At the end the computers will predict all words.

But there will be no one left to understand them…

“To be or not to…”


The computer will predict the word.

But it will mean nothing at all…