"Before I recuperate my university fees by committing insurance fraud." Classic

That vehicle isnt stopping due to any proximity sensors, its just intimidated by the almighty levitating banana.

The funniest adversarial attack I have ever seen is: a piece of paper with 'iPhone' written on it, incorrectly identified as an iPhone.

Imagine walking next to this guy and hear “this car thinks I’m a banana, so it’s going to run me over”

Can't wait for the cyberpunk future where we all run around with giant bizarrely patterned sheets over ourselves so that the robocops think we're all bananas and won't report our crimes

As a human, even after recognising a kangaroo, I still have no idea what it is going to do. They can, and do change direction mid jump.

"This pattern should confuse it enough into thinking I'm a banana." This seems like a good channel

Excellent intro to AI. As someone in this field, I have a few comments: 1. For detecting straight lines, the Hough line transform is the better, more efficient approach to use. 2. The RGB values of objects are too dependent on lighting conditions to be useful in most real-world situations. One solution is to convert colors to HSV space and only look at the hue component.

I can’t wait for 2045 Self Driving Patch Notes v2.6.7 - Road line distinguishing improved - Dynamic Weather Analysis added - Car will no longer slam the gas when it reads a school zone sign

The unique thing about this guy is the many on screen graphics and varied filming locations that just make his videos 10x more interesting!

Human “vision” includes a lot of understanding. Think about how hard it was to learn how to drive, even as an almost adult human. And how much concentration it takes to safely drive, especially in difficult and dangerous situations. Good luck with AI!

"The book is still a book" Screen shows clock and alarm clock as most likely answers as to whats in the image.

That first blobby picture does look like a toaster though, at least that's what I immediately picked up from seeing it in my peripheral vision

"Or can spot a lion, hiding away in the long grasses" Meanwhile the safe and unsafe switch sides.

A couple of key points that weren't covered here: These adversarial images are AI specific, in this case generated for Google's AI in particular. If you showed that shirt to a Tesla, it won't think you're a banana. Other major point, most AIs nowadays aren't actually built like this; more popular techniques include back-propogation, or gradient descent methods that are based more on mathematical theory than evolution like we see in nature.

You have a ton of potential, James. This channel is a hidden gem, I can see you becoming the next VSauce.

“If the impact doesn’t kill you, the farmer will” Given how fond of ice cream I am, the farmer sounds pretty understandable to me.

The question is, can I make an AI take over the channel for me? And would anyone notice if I did?

This was a great video! Very informative and you pulled a sneaky on us at the end; definitely a little more confident in self driving vehicles but more knowledgeable about it's limitations. Thanks!

That array of stop signs triggered Sesame Street memories. "One of these things is not like the other. One of these things just isn't the same..." That round stop sign is one I've never seen. I've even seen home-made stops signs and they're at least somewhat similar to an octagon. One was not even red anymore or even had the word STOP on it due to weathering, and it still worked.

10:49 - "Classified as the pure essence of a toaster" By the Omnissiah, this is making me harder than terminator armor.

12:39 "The book, still a book" Pretty sure that's an alarm clock

This video/production quality was incredible, I was fully expecting you to have over a million subscribers, keep up the great work!

Fascinating video! Thank you. I knew nothing about this topic coming into the video and left feeling like I genuinely gained a broader understanding. Much appreciated, watch out for buses! :)

I really hope you continue this channel after you graduate. You’re a natural.

Just posting a comment for the algorithm. I really want to see this channel grow.

Speaking of Google AI training, they also make use of the CAPTCHA images we all know and love, to train their image recognition algorithms. Whenever we come across a CAPTCHA asking us to identify all squares with a lamp, stairs etc. to prove we are human, we contribute to improve their AI by confirming/rejecting choices already made by the AI.

The main take away i got from this, is that we can make an image, that is the quintessential ultimate integral essence if a toaster

If you've never appeared on Tom Scott, it might take extra 2 years for the algorithm to get me to you.

"The book is still a book" AI: *C L O C K*

2:55 Why is my ad-blocker a stop sign now?

okay but i want to say that you gave the simplest and yet most understandable breakdown of neural networking i've ever head and i am extremely pleased by that

"They don't need to be perfect. They just need to be better than humans."

As a fellow Perthian, its been a hoot trying to figure out where each of these shots were filmed!

Blown away by the production on this video and the content. This kid’s got a future (and the team behind the scenes)!

11:46 "We could also cross reference the government databases which store the location" of all the people in the country which we don't want to hit with a bus. I was amazed how far into that sentence my prediction remained accurate. The visuals even helped.

I was impressed with your dedication to travelling to all the different filming locations around Crawley, Kings Park and West Perth. Great intro to the complexities of vision AI. I'll be sharing with my students :)

Hey James, great video as always! Just one small gripe from a somewhat experienced AI developer: while the process you describe at 7:47 is real, and has been used to train some neural networks for some tasks, it's not how any vision-oriented network that I know of is trained. What you described is a genetic algorithm, but most modern nets rely on some form of gradient descent and supervised learning. This process also starts with a random network that spits out gibberish, but rather than making random mutations and combining it with other ones, it uses only one network and makes small strategic adjustments to it in an attempt to minimize one (or many) values, called the loss. The loss is calculated after every step by comparing the network's output to the expected output, and we can then do some "backpropagation" to figure out how each weight would have to be adjusted in order to reach a result that's closer to the one we want. This is possible because we have images that are labeled (usually by an overworked and underpaid undergrad student) with the expected output, which allow us to nudge the network in the right direction. If we do this enough times for enough images, we should get a network that can reliably predict things within that dataset. Thus, the more diverse the data we have in our training dataset is, the better our network will be at dealing with previously unseen situations. You can even go one step further and do what's called "adversarial training", whereby you find these pictures that will trip up the network and intentionally include them in your training data, with the right labels of course, in an attempt to make the net more robust against them. Hope this helps!

This video was very interesting, mostly because I live next to almost every shot in the video! Perth for the win!

Regardless of the information within this video, I was most impressed that there was not a single jump-cut. Well done. Excellent work.

Neural nets don't (usually) get trained with genetic algorithms, buy with some form of a gradient descent learning algorithm. Genetic algorithms do get used for setting the parameters of that learning algorithm. Adversarial attacks only work on an specific trained network, and those same attacks could no longer work once the network is retrained. A lot of AI systems actually go through another round of training where they are shown a set of such adversarial attacks. After that, the network is less vulnerable to them, but at the cost of accuracy. In some cases it's actually safer to keep the adversarial attacks weakness, as those are way less likely than the situations in which you are giving up some accuracy.

I'm so happy Tom Scott promoted you! Great content! :)

I just realized that I watched this video when it was first posted, but then for some reason it was only just a few days ago that I ever watched another Atomic Frontier video. Not sure what happened, but it was a funny realization that I have been here before.

this is wonderful!! keep up the amazing work dude

This video really shows how easy it is to forget that we inherit some of our parents abilities and their parents abilities and so on, and the fact that our brain has been in development for millions of years by this point

From Breakthrough Junior Challenge Finalist to this - Congrats James!

Sup fellow Perther! i live in the hills (kalamunda) and am really fasinated by ur work. i hope to work at UWA under Chemestry one day and you are a real insparation

@2:20 I work in the field of machine learning and computer vision and I never heard this explanation for human's big brains before. Will totally be starting every public speaking opportunity with that explanation going forward.

I've never heard of neural networks being trained by generic algorithms, and never heard of such training affecting the number of layers and the number of nodes per layer (in your simple vs complex example where the simple is deemed more fit when the results are the same). Neural networks are typically trained by using "back propagation", which you never described in the video.

“Once, men turned their thinking over to machines in the hope that this would set them free. But that only permitted other men with machines to enslave them.” ― Frank Herbert, Dune

13:08 this is what would be referred to by certain people as the danger of "but sometimes". Most of the time, the AI can recognize a stopsign and stop, BUT SOMETIMES it doesn't. Failing yourself to recognize that it's far more likely for a human to either not pay attention and see the stopsign or to just choose to ignore it. Those are things that happen ALL the time. I'd trust my life to the AI every time.

An important note here is that adversarial patches are generated to trick the specific neural network which they were generated from. You cannot expect an adversarial patch from one neural network to generalize to other neural nets. It probably has less to do with the engineers improving the networks (which they certainly have done) but rather the fact that any change to the neural networks whatsoever would lead to a different set of adversarial patches needing to be generated to fool the updated network. TL;DR: The adversarial patch problem has not been 'solved' by Google engineers.

your intro is so good, "so it will think I am a banana and run me over" and "recuperate my university fee by committing insurance fraud" wow, 2 amazing lines in the first 35 seconds...

7:52 The process you explain here is not the normal commonly used approach to train neural networks, the normally used way would be using gradient descent (for supervised learning as in this case), what you explained is using genetic algorithm like NEAT, which are useful but not so much compared to gradient descent in this case.

So I am currently doing a research project in machine learning, and I noticed two issues in your explanation. The model that you described is a multilayer perceptron(MLP - built entirely of fully connected layers), and although they are capable of classifying images, they are no where near as good as convolutional neural networks (CNN - which are translationally invariant). Most image classifiers use a few convolutional and pooling layers, which is then passed to a few fully connected layers. Many tutorials use MLP for image recognition to teach fundamental theory, which is probably where you got the confusion from. The training method you described is reinforcement learning, and although this is a popular method for training models for other tasks, it is not great for training image recognition. A much more suitable training method for image classification is Adam optimization.

2:07 Oh, good, these berries here are the safe ones. Guess I'll eat them now.

The "talking banana" angle is an interesting direction for the channel, but I think it has potential going forward.

Can I just say that your audio is somehow much better when recorded on set? Of course, there are the surrounding sounds that also get picked up by the mic but it sounds more natural and I quite like it!

You should read about generative adversarial networks or GANs for short. It's a technique that aims to avoid overly simplistic criteria for identifying things by training not just the classifier network, but also an adversarial network that's being trained for the precise purpose of trying to fool the classifier and using that to train the classifier to not get fooled so easily. A lot of the more impressive advances in AIs seem to be done using GANs lately. Also, it's worth noting that programmers working on AIs aren't working on patching individual errors, but rather looking for ways to improve the training process so that it's the AI that learns how to overcome them.

This was a really well made and informative video. But there is one issue where the stop sign suddenly becomes a 45 speed limit sign, other than that, this was a great video.

Love to see a good KZfaq channel growing.

It still feels so cool to see my own city and University represented on the science-y side of KZfaq. The super high quality of these videos is even cooler 😄

Machine learning usually use backpropagation. The neural network will output a "confidence score" for each category. It will then check what happens when it changes its nodes just a tiny bit, and try to nudge the values in the "right" direction.

I really like the way this is filmed! Awesome!

I am so happy to finally find a channel that is aware of the need to educate visitors on the dangers of dropbears!

Good job with the not-voice over!

Extremely high quality content. I felt as if I was watching something from 90’s/00’s Discovery Channel in 4K

AI Recognition Software: Bro it's fine, it's just a banana. Just go. Proximity Sensor: If it's a banana it's a HUGE BANANA oh my god STOP

So glad to see your views and likes are going up! You have been creating high quality, interesting content for a long time without getting the recognition you deserve. Keep going bro!

Discovered you today. Wow. Amazing. Exceptional quality, clear audio, easy to understand and a very joung talented boy. Hope i sre you grow, very well done

I didn't realise how cool it would be to see B-roll shots of the city I live in! Perth is so rarely put on display like that

New subscriber that's loving your content. Great work!

Really liked your personal little experiment in the end, instead to just talk about the news headline and leave it there. GJ, as always ;)

From one aussie to another: You're a bloody legend mate! Fantastic videos!

Totally lost me in the first few minutes, but I stayed to find out if you were going to get run over.... Great job, excited to see what comes next from you!

If you look at it carefully enough it actually does look like a psychedelic toaster

5:58 Just gotta love the Kangaroo skiing in the bottom right corner

I just discovered this channel, and I already love it. It’s like a combo of Tom Scott and Fact Fiend, two of my favorite creators!

I’m waiting to see this guy on science channel or discovery commentating or hosting. Love the vids!

How do you not have more subs?! This channel is great

The audio is so, so much better in this video! Really great improvement.

Wow! Amazing video as always! A thing that I wanna point out is that the probabilities shown at your experiment (12:00) decreases a lot when the Adversarial Patches are added. Google improved for sure its IA, however the Patches are still making an impact on the classification.

2:30 that's actually really neat, and probably explains why we can "visualize" things in our head, or how the most vivid hallucinations are visual ones

Your channel is grown a ton good job

I remember when my National Geographic Kids magazine in 2005 or so predicted we’d have self-driving cars perfected (as well as color-changing clothes that we can tell our mirror to switch), but I don’t think those writers understood how woefully complex AI could be back then...

Found this channel on the UWA site. Great work

I have no idea how self driving cars work, I could figure it out most likely, but some of the stuff you're talking about I have worked on in making a video game bot, I was training the bot to have computer vision, detect objects and shapes and pick them up if they were good, avoid them if they were bad, and learn from their successes!

Hey @Atomic Frontier you're really fucking smart, thats wild that you can do all of the stuff you are explaining

"Sometimes a banana is just a banana, Anna" -- Sigmund Freud

Fun video! A few corrections to keep in mind, though. 1.) Neural Networks used in vision and self-driving don't tend to use genetic algorithms (the evolving style you mentioned here). Not only that, but even if they did use genetic algorithms, it would use a NEAT-like algorithm, which starts with a sparse or empty network which slowly gains neurons through mutation. No, most computer vision use tried and true backpropagation methods, like Stochastic Gradient Descent (SGD) where the weights of the various neurons are corrected by comparing the output of the net to some target value, and adjusting the weights based off of that difference and a pre-determined (or adaptive) learning rate. 2.) The issue of adversarial attacks isn't just a matter of network complexity. In fact, a paper a few months back even found that simpler networks tended to do better, because small incorrect regions had a lesser impact on decision making. It's sort of like displaying an image on different resolution screens, with a higher-res one able to pick out more details, but also more likely to notice errors. On the lower resolution screen, you can't tell the difference. Obviously, that comes with its own pitfalls, but the point is that adversarial attacks predominantly work against specific forms of vision, and often exploit specific shortcomings (such as interpreting the blob of colors as a toaster, because it hits all the same buttons as the toaster). 3.) Most forms of self-driving vision (and controls) are different. Tesla uses a segmented neural network (with each segment helping identify specific items within the world) using a shared input, while Comma AI uses a more end-to-end design, and Waymo just uses Lidar and can only work within specific pre-mapped areas. While Tesla and Comma AI both use Neural Networks IIRC, different attacks would likely be required. 4.) The best way to stop adversarial attacks is to feed the network enough data that its generalizations are....well, accurate generalizations. Give it noise, different perspectives, lighting, everything. Essentially train it to the point it's not using a short-cut interpretation, but rather a more robust, almost human-equivalent interpretation. As a black box, though, it's hard to know when enough is enough. Thankfully most self-driving projects still have redundancies. :P

4:50 Hough transform does that finger in the nose. And I improved it to recognise any shape, so you can teach it to recognise lines, squares, or kangourous ... Its as simple as a convolution filter. If you find that the object recognised has a very good probability ratio, then just recompute your filter form the new image to adapt to its changes. This allows to follow in 2d an object moving in 3d ( including adapting to a tracking camera, or an item turning on itself ).

7:23 computer: this is clearly the letter A Me, the product of billions of years of evolution: amugus

1:35 Just gotta love the Swiss cheese building behind him

Great video. Now get some more coffee and do your lit review / finish your thesis.

4:00 Speaking of international recognition of signs, I recognize that "today's fire danger level" sign in the background. Greetings from Utah, US. Keep up the good work.

hmm Once we get them nice Hyperspeed Quantum computers, plus some insanely detailed... Laser distance sensor things, we found use the physical distances from every point on an object, to render a 3d mesh, and base our prediction off on that

Wow, never heard of the bobtail before. Australia has some truly weird animals.

Ha loved the "Dingley road" easter egg. Great video!

As someone who rides in Google's self driving cars regularly (just as a hobby), I really love this overview and learned a lot! Thank you!

Love your videos always helps me fall asleep at night :)