I have got physically things in front of me.

I'm gonna also got appear, but I'm hugely hugely excited about.

Unfortunately from our group.

I really wish I could say it was from a group.

We've been interesting this type of thing for for many years, So as you can see, it's his autonomous scanning problem across could be in situ tip conditioning through machine learning.

And this is from Bob Locals Group in University of Alberta on Dhe.

It's, ah, phenomenal piece of work.

Why, I think it might be of interest or computer file audience.

It could also be of interest of 60 symbol Jordan's.

But for this in particular, it's basically controlling the atomic structure of matter through machine learning.

So it's really the interface between physics and computer science.

First of all, it's all about scanning probe microscope.

Now.

I think we've talked a little bit about scanning quote McCroskey, but in essence, what we have is a sharp tip, preferably atomic Lee Sharpe, with one atom sticking out the end, and that sounds really difficult to do, but in practice, not that difficult to do but it is difficult to control is just how many atoms stick out the end on the arrangement of the atoms of the end.

And that is really the been of any scanning problem across campus life.

But let's say we've managed to create this regard.

One out.

I'm sticking out the end.

Here's our surface.

Here's our sample.

You bring it in and you move it.

So you all most of the talking point, sometimes even after contact point, whereby you have a very small separation between the tip and the sample.

So what we have is our sharp tip.

We bring it in really closer surface, and we do that using Piazza electric crystals.

Actually, those barbecue lighter things that you use when you click the end Peter Electric Crystals in those you bring in really close within an atomic diameter or so, and then you move across the surface on what you're picking up on is the interaction out out?

I'm right at the end off the tip with the atoms of the surface.

She moved back and forth, back and forth and build up an image that way.

It's a slow process, but it's a process that is incredibly precise on were sacrificed speed for that precision on the other.

Great thing is because it's a probe as well as imaging.

What you can do is you can deliberately try to manipulate the surface so you can bring the tip in bond and try to pluck atoms out, for example, or if their atoms absorbed in the surface.

You can train, slayed them, move them across.

And we're now at the point where in many cases we can slide atoms of will across the surface to spell out different patterns bought, bought, and there's a big boat.

As I said, the key thing here with scanning court my cross could be is controlling the structure at the end of the probe.

And so we'll start off.

We will take our tip on the way we create our tip.

The first stage in creating the tip is we put it into a solution solution of sodium hydroxide and all.

This is chemistry of the computer file audience.

Bear with me, you wretch it down to a sharp point, but that's not good enough.

Generally, it's not good enough.

Then you put it in your vacuum system.

You move it in.

You'd like to be able to see atoms, but most the time You don't see Adam.

So what do you do?

Well, you play a little voltage pulse to try and jiggly atoms around at the end of the probe.

All your players increasing the current and that can lead to effects which will move the atoms around at the end of the probe.

That doesn't work.

You cross it gently and that doesn't work.

You cross it a little bit further in, Doc doesn't work.

You drive it in half a millimeter or so when push it around and try to try to jiggle it around.

How do you know if it's worth very, Very good question.

You go.

Does this image look good?

Really?

Yeah.

What we really want tohave is as an image where by what we're seeing is the structure of the surface and that this has little influence is possible.

So what we really want to do is have a sharper probe was possible because, for example, if we have a probe that looks like this where we've got a flat plan where each one of these atoms, we could it potentially contributed the image that can lead to very confusing images.

Because you've got multiple different imaging centers.

Let's say we have something like this, so it comes in like this to the surface where you've got an hour from here on out.

I'm here on both of those can contribute to the image, and sometimes it'll be tilted slightly.

And this one can contribute Maur because it's closer to the surface.

But this one can still contribute.

It's reasonably close to the surface, so those are double tip images.

The band after scanning more probe microscope.

It's life because really what you want to do is to get right down to the atomic level.

At the moment.

What happens is students postdocs researchers sit in the lab, and they they literally just trial and ever push the tip into service, apply a voltage pulses, try and coerce it into the state they want.

And it's a massive bottleneck.

Massive, massive Barton like when in fact, what we'd want is, ah, sort of auto tune or an auto focus.

Borton, where you get to the end of the day if experiments, experiments might have worked, okay, But perhaps your tip is not in good stead, and you want to press a button, which is optimized probe on go home and then come in the morning and do your proper experiments instead of driving yourself to distraction.

Just pushing the tip into the surface to try and change the structure.

The tip and that's been a long time coming.

Scouting party across the bay has been around since the early eighties, and we're still at that level.

Many man Nottingham's no different many, many groups are still at that level where it's a, you know, a PhD student in their second year, literally banging my head against the table, going Please work.

That's why this paper is so important.

And it sze really nice.

So what they've done, they've trend.

A convolution of neural Net on.

There were many, many good videos about your nets and convolution, urine lattes and computer file.

Mike Pound has done a number off really good videos.

I thoroughly recommend them.

That's what they've used.

They managed to train it to distinguish between when it's gonna double tip when it's got a proper single atom tip on dhe.

They've gone that extra step, and they've modified the probe so that it will recover the structure.

You need to get a good single atom images that where this is a really big leap for dinner.

For May, it's it's really exciting.

I'm slightly disappointed that we didn't get that.

We've been working on this type of problem for a number of years.

Actually, no, no.

The good reason why it's good to do Computer five video this actually, computer scientists here in Nottingham on a number of years back, we tried to employ what are called evolutionary algorithms or genetic algorithms to try to tune the probe.

That way it worked, okay?

It didn't work particularly well all the time on the way to go.

Obviously the next step, the next evolutionary stage.

And that was to go to the machine learning side of things.

And I actually had a summer intern working on this last year.

But we just said we were beaten, pipped to the post.

The great thing is, is where it can go because they have controlled the probe on they've been going for a particular atomic resolution, but actually sometimes particularly want to do chemistry.

Let's use this one, actually, sometimes that that Adam sticking out.

The end is what you need, but sometimes what you might actually need just in terms of the chemistry in the arrangement of the electrons.

If you really want to manipulate atoms, you want to do chemistry, computer control, chemistry.

You might actually need a structure a bit more like this in terms of Highwood bonds and how it interacts with the surface.

The next step in this is too not just give us a good tip, give us a tip without particular structure.

Give us a tip of the particular state, and then we're really not just controlling matter at the atomic level.

We're controlling the right down in the single chemical bond level, and in fact, we're controlling the right that the quantum mechanical structure of the tape when we go a little bit further along these lines, you know, can we actually just tell it we wanted to build something like that?

We just wanted, you know, can we get the computer toe a CZ long as us within the laws of physics?

That's our blueprint.

You know, when that might be a chunk of silicon, can we actually get it to build out your calibrating a camera.

There are various tests, images that you can use to to calibrate it, being white balance or focus or whatever.

Is there an equivalence in this that's effective?

You want to know when they talk about a single tip versus a double tip?

This is a pro.

This is a sample.

So what we'd like is that the radius of curvature, the sharpness of this is smaller than the object.

We're actually emerging at the surface, so if we do that, we'll retrace it across with map out.

Ah, an image of what's happening at the surface.

However, that's just by symmetry, exactly equivalent to that.

So if you have a relatively blonde tip like a double tip, or like a triple triple quadruple triple closer on, you got something sharp at the surface like a single atom or a single bond that sticks out of the surface.

Then what will happen is that this will image this.

So this is our test structure to comment.

Thio, Muppet across to the video process.

This is our test structure.

This is a lioness to say what's happening at the end of the probe, and that's exactly what they're doing in this.

They have single bonds which are sticking out the surface.

When they see these sort of ghost like images, it's telling us about the structure that tip rather than stuck to the surface, and then they control it accordingly.

So this is our control.

It's built into the experiment, and you expose the plastic of the surface in particular regions according to the pattern on.

The important thing is when the this particular polymer is exposed to light, it becomes soluble the region.