Viewing profile — aifer4

This is a perspective article I wrote with a number of researchers in unconventional computing, about solving problems in AI using physics-based chips. There is also a video of me …

Latest research from Normal Computing

I've been meaning to start this blog forever, and this is my first post

> I don’t know what I may seem to the world, but as to myself, I seem to have been only like a boy playing on the sea shore, and diverting myself in now and then finding a smoother…

You're right, that iterative methods may be linear in time with respect to the number of parameters. In this paper, we provide a method which is linear in time with respect to the …

To answer your question about sorting an array: For an array of length n, where each element takes one of m possible values, there are n^m possible arrays. But there are only O(n^m…

The Optical Fourier Transform (OFT) in [2] is a way to compute the Discrete Fourier Transform (DFT), and is an alternative to the Fast Fourier Transform (FFT). The OFT basically do…

The relationship with Hopfield networks sounds fascinating, would love to discuss further. As you mentioned, there is a connection to annealing in that we are encoding the solution…

Had a quick read of [3]. This work comments on three contributions to the error in an analog scheme to solve linear systems via an ODE that is encoded in the circuit dynamics, alth…

We do not (yet?). Here is a simulation I made of similar hardware demonstrating the equilibration step of the algorithm https://app.normalcomputing.ai/composer/playground

https://app.normalcomputing.ai/composer

An interesting feature of this approach is that the proposed hardware doesn't rely on non-linear elements, memristors, or even active elements (besides an optional noise source). I…

You mentioned that such problems may be solved by solving a linear approximation of the non-linear problem (and I am in no way an expert in non-linear optimization). To the extent …

One way to think about these methods is that we are essentially implementing a Monte-Carlo algorithm physically, where on each "iteration" there is a matrix-vector multiplication. …

These results probably would not hold in the same form for a quantum system. By a quantum system, I mean a system where the decoherence time is on the order of the other timescales…

Straying a bit off topic, but I think one of the more sensible approaches to information-energy equivalence is a thermodynamic engine with an information reservoir (in addition to …

Definitely. Landauer's principle gives a lower bound on the amount of energy a computation requires, which is k_B T ln(2) times the number of bits erased in the process, the decrea…

This is an important observation, and is one of the reasons we included an energy-time tradeoff analysis in the paper. To our knowledge, this is the first result where the product …

Good question. There are different ways that errors come into analog computations, including thermal noise, measurement imprecision, and imprecision of the device's physical parame…

Latest research from https://normalcomputing.ai/ . Feedback welcome!

This is a great technical demonstration of how to visualize a circuit board. But I would rather walk over hot coals than try to actually design a circuit using this interface. Circ…