I’ve had quantum computing on my mind and another tech talk went by titled Quantum Machine Learning and I had to jump on it. The talk is by Seth Lloyd from MIT.

The talk starts out with a quick overview of quantum mechanics. He gives a mind bending example of a CD that holds about 10 billionÂ bits that can be turned into a quantum state with a single photon. The problem is it’s not in a form that you can readily manipulate. This problem of developing natural systems that can innately quantum compute is one area that interests him.

The heart of the talk is the description of how to perform classical linear algebra operations using a quantum computer in order to get an exponential (logarithmic) speedup. This is desirable because simple (although computationally expensive) vector operations underlie a lot of computer science in general and machine learning algorithms specifically.

The quantum versions of linear algebra operations Seth focuses on are:

Manifold learning (finding holes and connected components)

He comments that you don’t get everything for free, it is taking serious work for them to map useful algebra into the crazy world of quantum mechanics. The explanations he offers appear quite intuitive (he’s a good communicator), although I expect they are deceptively complex once you step into the detail. It’s not really my area.

Hello Dr. Jason,

Thank you for sharing this interesting post. Have you tried to use Quantum Computing with machine learning or deep learning.

Thanks.

No, I have only read about it.

Thanks for sharing! In your opinion, will the benefits of quantum computing will outweigh the benefits of using TPUs in deep learning?

Thanks in advance for your time and attention.

Yes, by far.