All Quotes

"In some sense, this is a thing that people have thought about for a long time, right? This would be like running some kind of evolutionary algorithm or some search or simulation inside the factory. And it's very attractive, but I think generally speaking, hard to make work well. So the question is what should I do, right? I could maybe I can set up this whole evolutionary setup somehow. And then I could just snooze for a really long time while some very complicated program tries to figure out the best robot program to put in the head of the robot. But I don't know. I am simultaneously too impatient for that."

"And so then the question is can I somehow take pieces and parts of all these ideas, some human programming, some robot learning in the wild, some kind of search or evolution offline, some inspiration from humans. Can I take all those things and put them together and see if I can find a way to engineer intelligent robots? So that's basically what I'm up to."

"I'm going to-- well, no. OK, let me say something about this. So then the one way to view the research agenda is to say that first of all, I'd like to be inspired by what we know about humans. And in particular, I'm very interested in this bulky core knowledge type stuff because that tells me something about what evolution, in some sense, saw fit to engineer into natural intelligences. And if I understand that natural systems seem to be born with a bias or some built in structure to think in terms of other agents, to understand that they move through 3D space, to talk about, think about objects as clumps of matter that cohere, that's a very helpful engineering bias for building a system."

"I also know just some physics and variance about the worlds that my robot's going to operate in. And maybe humans don't have this built in explicitly, but they almost surely have a built in implicitly. And I also have some other constraints as an engineer who's trying to make intelligent robots, which is that humans are the engineers, right?"

"So if humans have to engineer a very complicated system, then it has to be the engineering process has to have some modularity to it because humans are really bad at understanding one big messy system. They're good at understanding pieces and parts that work together. So it may be that we have to take a modular design approach in our engineering efforts for intelligence, not because the intelligence needs to have that architecture, but because we, the human engineers, need those tools for actually building a system."

"So all these constraints need to somehow come together into a way of building intelligence systems. Actually, I would stop here for a minute just because it's a convenient spot and see if there are questions. I see some red Q&A button. So maybe someone can ask."

"Yeah, actually. For years there has been. So a more typical formalization would be in terms of predictive models and planning or reasoning. So reinforcement learning. Also, it depends. The phrase unfortunately, the phrase, "reinforcement learning," grows and stretches too. And sometimes for many people and in many discourses, it's come to mean all of intelligent behavior, in which case, I would say, well, no it's all reinforcement learning. But that's vacuous. Other formulations involve reasoning about objects and their relationships and thinking about the long term consequences of taking actions in the world and so on. So there's really different ways of framing and formalizing the problem. And they give you very different computational profiles and different learning strategies. OK, good."

"So I'll just tell you some story because people usually like stories, and it's kind of the afternoon. So and this is related to the question about reinforcement learning, probably, right? So how did I get into this whole thing? When I just finished my undergraduate degree, which actually was in philosophy, weirdly enough, I went to work at a research institute while I was starting my PhD. And they had this robot nobody really knew actually very much about robotics. So And it was my job as the brand new person to try to get the robot to drive down the hallway."

"And so what happened was I programmed the robot. And it would run into the wall. And I would bring it back. And I would fix the programming. And it would run into the wall again, hopefully for a slightly different reason. And over the course of a couple of weeks, I managed to write a program that would use these funny sonar sensors on the robot and make it drive down the hall without crashing into the walls. And so that was good. And I was happy, in a way, at the end of that, that I had gotten it to work. But I reflected on that a bit more. And what I decided was that I had learned how to navigate down the hallway using the sonar sensors. And what I thought was that-- and it had taken a long time. And I was kind of a hassle. And really, the system should have been doing the learning, not me. So my view was that I should figure out a way to get out of the loop to build systems that could learn on their own to do stuff. And then I could just wait for them to do that. And that would be better. So that was flaky."

"Then I sort of reinvented reinforcement learning in a not very good way, really. But it was kind of entertaining. And I this is a slide by the way for those young people in the audience. You might know, but back in the day, we used to write with colored depends on pieces of clear plastic. And that's what we used to give talks. So I had this kind of pseudo reinforcement learning thing. And by 1990, I actually had this little robot called Spanky that did actual reinforcement learning during my actual defense. So it didn't learn anything too complicated. But it did do it in real time. So that was kind of fun."

"So OK, I finished my PhD. And I thought, OK, I know something about robot learning now. But I really want to make robots that can do complicated things. And I couldn't figure out how to get basic reinforcement learning methods to really scale up to problems that I cared about. And so this is one last flight. I'll show you from some talk that I gave in 1995. And I kind of complained that the ideal that you could take just a big bunch of what I like to call neural goo now, just a big bunch of generic neural network stuff, and train it to be an intelligent agent all by itself. But that wasn't going to be feasible. And instead, we needed some kind of compositional structure. And that would give us more efficient learning and more robust behavior and so on."

"So I'm still there, OK? So I'm still in I'm still trying to figure out how we can design an architecture that can learn efficiently. And so the research strategy that I have really adopted, I work closely with a colleague, Tomás Lozano-Pérez. Our strategy has been the following, which is to try to think of some very generic representation and inference mechanisms and build those in and then figure out how to learn the rest of the stuff. And we're all used to I think by now the idea of some representation that inference mechanisms that we would want to build in."

"For instance, everyone's used to the idea of convolution now in image space. But if you think about it. And I've had people tell me who work on convolutional neural networks that they don't build any structure into their system. It's just a neural network. But of course, as soon as you build the compositional structure into a neural network, you are taking a position on some regularities that are in the input signal and so on. And you're taking advantage of that so that you don't have to learn a whole fully connected network, but you just learn some compositional kernels."

"So just as convolution gives us a great leverage when you apply it to the right part of the problem, then the intuition as well, hopefully there there's a few mechanisms, hopefully not like 100 mechanisms, but maybe 10. And then if we figure out how to use those mechanisms to bias learning and to structure behavior that we could learn robust ways of behaving that are efficient and so on."

"So one set of possible kind of general ideas includes convolution in space also and time. Maybe understanding the kinematics of the system that it's connected together in joints and segments, a notion of planning to move through space, being able to do causal reasoning-- if I were to do this, what would happen? -- Abstracting over individual objects, various kinds of state and temporal abstraction and so on. So our view-- I don't want to commit to a particular list-- but is that there's a list of structural principles that are pretty generic and very broadly useful and we should build them in."

"OK, I'll keep going. I'll surely be able to offend some people soon. And I'll work harder at that. OK. so if we kind of accept this idea that we're going to build in some structure, then what? And the thing that my colleague and I have done recently. Well, now, maybe not super recently, but recent. In order to test out the idea that there's a set of mechanisms that would work well, what we did is we hand built the rest of the system. So we hand-built some transition models, inference rules, ways of doing search control and so on and connected them up to these general mechanisms and made a system."

"And just again, to kind of give you the motivation. I really want a robot. This isn't my kitchen, by the way, just in case you were worried, my kitchen. But imagine that you had to clean this kitchen or make breakfast in it or something. It would be very hard. And imagine programming a robot to do it. It's extremely hard. And so one thing that's useful to do is to think about what makes this problem hard. So one of the things that makes it hard is that there are lots of objects."

"If I could change anything, then it would be the way society looks at people with different disabilities."

"I hope the campaign will reach every child in my country, so that everybody grows up healthy."

"One of the most difficult things for a child, is to be among other children, but feel different, in a country where disability is a stigma."

"I suffered a lot from the negative way people in my community looked at me when I was a little girl and as a teenager, and certainly I felt very sad and in all the stages of my life as I tried to overcome the feeling that I was less than the other girls. But, thank God and thanks to my family, I could overcome that."

"Let your children get the vaccination against polio. A small dose will prevent a big disaster."

"The difficulties and stigma I faced due to polio challenged me and turned me into the Sara Gadalla that I am."

"I was doing digital marketing for a guy selling men’s clothes, watches, and other men’s outfits."

"I would read about the trending fashion styles and then copyright."

"I did it for some time until I thought of creating an agency to do online marketing for other businesses."

"Not only did I grow to love fashion, but I always wanted to challenge the status quo because when I was growing up, I observed people's mindset towards my mother as a fashion designer."

"People often said that tailoring is a job for the uneducated."

"I wanted to change their mindset that it is not for the uneducated but also the reason people can not walk naked."

"Women have been so discouraged by coffee in a way that, when you look at the coffee value chain, women do the donkey work. When the coffee is ready for selling, men step in to claim the proceeds. However, when a woman sells coffee, she has a hand in it."

"We want to solve the problems that have been engendered by the success of search"

"If you have 20 researchers interested in search, then getting them together where they are cross-fertilizing ideas, you make something bigger than its parts. You can create a nuclear reaction"

"reuse is properly a process issue, and individual organizations need to decide whether they believe in its long-term benefits."

"The problem with traditional approaches to abstraction and encapsulation is that they aim at complete information hiding. This characteristic anticipates being able to eliminate programming from parts of the software development process, those parts contained within module boundaries. As we've seen, though, the need to program is never eliminated because customization, modification, and maintenance are always required-that is, piecemeal growth."

"reuse is easiest within a project instead of between them. A manager's success depends on performance on a given project and not on performance over several projects. And preparing code for reuse requires additional work, not only by the reuse expert but also by developers. Therefore, preparing for reuse has a cost for any given project."

"Habitability is the characteristic of source code that enables programmers, coders, bug-fixers, and people coming to the code later in its life to understand its construction and intentions and to change it comfortably and confidently."

"One of the primary reasons that abstraction is overloved is that a completed program full of the right abstractions is perfectly beautiful. But there are very few completed programs, because programs are written, maintained, bugs are fixed, features are added, performance is tuned, and a whole variety of changes are made both by the original and new programming team members. Thus, the way a program looks in the end is not important because there is rarely an end, and if there is one it isn't planned."

"The lesson to be learned from this is that it is often undesirable to go for the right thing first. It is better to get half of the right thing available so that it spreads like a virus. Once people are hooked on it, take the time to improve it to 90% of the right thing"

"I try to find people who shore up my weaknesses"

"We get so stuck on our own viewpoints — we need help to be shown other options"

"If it’s the right thing to do, you push your qualms aside and you do it"

"Leadership does not come from the top down,Gaddis said. It comes from the bottom up"

"Go with your gut but use your brain"

"Hard work, knowing my personal power and working with an extremely talented and dedicated team is a big part of my success…After reinventing myself many times over, it is a great honor to be on the cover of Texas CEO Magazine with the hopes of inspiring other businessmen and -women to take big leaps in their lives and careers"

"If someone calls me authentic, that’s the biggest compliment they could give to me"

"You need ‘rough riders’ in your life – the people who will shoot straight with you. They can call bullshit on you, they can tell you how great you are"

"As well as the human remains, the jawbone of a was unearthed at . Lynx became extinct in the UK about 1,800 years ago, but I found it exciting to think of these beautiful, lithe creatures roaming over my home landscape. There were the bones of a 7,000-year-old that had most likely been dragged up to the cave by an animal. And a short distance away, in fact just an arrow's flight from Kirkhead Tower, is , the place where the last wolf in England was reputedly killed. And although this idea might be fanciful (how on earth would anyone know where the very last wolf died anyway?), there's evidence of wolves right here on the doorstep. had been roaming northern Britain over 1,300 years ago and their bones were found in the cavern. They had been gnawed by a large predator. The most likely candidate? Wolf."

"The remains unambiguous, but still the fox hunts continue. Since the ban came into force more than ten years ago, I've seen — or more often heard — a number of hunts in progress. I've heard hounds in tracking rapidly across the open ground of the higher s, their baying echoing around the valley. Or down by the , men with s, turning to see who was driving past. Up here in , the hunt has always been on foot, but for all the lack of pomp and , and money, I still loathe it."

"Thousands of , , , , , and are being planted, to create habitats of indigenous – of tree cover and open grazing. A flickered along the prickly spine of the new fence built to separate the sheep from the trees. Further on, beyond a bank of glacial , the infant disappeared behind a drystone wall above what was once a but has become a dry ochre basin of ' grasses. Canalised in a previous century, the Mint is to be re-meandered to its original course through the valley bottom, and Dub Ings will become a tarn once more. Like the new trees, this work – done in partnership with and another local farm – is intended to lessen the effects of flooding on communities further downstream; the memory of is never far away."

"In 1992, almost 2,000 of the world's leading scientists presented us with another way of looking at the world. In , they informed us that the current trajectory of was unsustainable. ... ... Some of us see what is happening but have little ability to act. Others see something else entirely because maintaining the juggernaut of the and is the priority. For them, the does little but get in the way."