This Image Breaks AI 

"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.

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

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!

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

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

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

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.

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! :)

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

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

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

this is wonderful!! keep up the amazing work dude

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

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

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

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

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

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

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.

I really like the way this is filmed! Awesome!

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 :)

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

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

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

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 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

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

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

From Breakthrough Junior Challenge Finalist to this - Congrats James!

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...

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

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

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.

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

Your channel is grown a ton good job

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

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.

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!

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

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

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

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

Thank you for the detailed explanation!

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

Love to see a good RU-vid channel growing.

Good job with the not-voice over!

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!

Loving the tok Scott style content super good but different enough from it that it’s unique good job!

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.

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

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.

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

“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

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

This is is a lovely lecture on image recognition. What a smart banana.

I get "Technology Connections" meets "Tom Scott" vibes from your videos. Nice. I'll subscribe

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...

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

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.

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.

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!

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

@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.

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

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!

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

Great video mate!

The thumbnail must of broke youtube because I'm getting this video recommended to me a year late

Found this channel on the UWA site. Great work

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

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.

As for that thumbnail, i don't think I'll ever read anything more glorious than 'adversarial bananas'

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

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

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

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

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.

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!

I love how this videi is just "don't be dumb" at both sides, while being informative and interesting.

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

Absolutely fascinating. My monkey brain caught typo of "neutal" net (time code 6:35) like those banana identifiers. Then I thought you had planted it for fun - just so I couldn't sleep. Our world needs amazing minds like yours to keep our roads safe. Also, please explain "drop bears", saw it on Bluey with my kids and still not sure wtf.

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

This video has been recommended to me once a week for a year now and for the first time I finally clicked it. Good video but no idea why it's always recommend to me.