--- title: "Meaning & Key Takeaway of: We now think of internal representation…" description: "\"We now think of internal representation as great big vectors, and we do not think of logic as the paradigm for how to get things to work. We just think..." image: "https://sms4smile.com/quotes/i/787/geoffrey-hinton-12991_everything_we-now-think-of-internal-representation_2993740.jpg" --- # We now think of internal representation as great big… ![“We now think of internal representation as great big vectors, and we do not think of logic as the paradigm for how to get things to work. We just think you can have these great big neural nets that learn, and so, instead of programming, you are just going to get them to learn everything.” quote by Geoffrey Hinton](https://sms4smile.com/quotes/i/787/geoffrey-hinton-12991_everything_we-now-think-of-internal-representation_2993740.jpg) [Download](https://sms4smile.com/quotes/i/787/geoffrey-hinton-12991_everything_we-now-think-of-internal-representation_2993740.jpg) [Open image](https://sms4smile.com/quotes/i/787/geoffrey-hinton-12991_everything_we-now-think-of-internal-representation_2993740.jpg) > “We now think of internal representation as great big vectors, and we do not think of logic as the paradigm for how to get things to work. We just think you can have these great big neural nets that learn, and so, instead of programming, you are just going to get them to learn everything.” [Geoffrey Hinton](https://sms4smile.com/quotes/author/geoffrey-hinton/) ## About This Quote This interpretation was drafted with AI assistance. It is one reading of the quote, not the author's own explanation. Modern AI focuses on large neural networks rather than symbolic logic, treating learning as the primary method. **In simple terms:** AI now relies on big neural nets, not explicit logic programming. Key Takeaway Embrace data‑driven learning over rule‑based coding. Themes AI machine learning neural networks Mood analytical critical Type technical philosophical When to use this quote - research labs - software development - education - product design - policy making Key Concepts deep learning representation learning Questions to Reflect On - How can we balance learning with logical reasoning? - What safeguards are needed for black‑box models? A Different Perspective Overreliance on data can ignore interpretability and bias concerns. ★ ★ ★ ★ ★ No ratings yet [Big Neural](https://sms4smile.com/quotes/about/big-neural-1935250/) [Everything](https://sms4smile.com/quotes/about/everything/) [Great](https://sms4smile.com/quotes/about/great/) [Internal Representation](https://sms4smile.com/quotes/about/internal-representation-4717978/) [Learn](https://sms4smile.com/quotes/about/learn/) [Logic](https://sms4smile.com/quotes/about/logic/) [Logic Paradigm](https://sms4smile.com/quotes/about/logic-paradigm-4717977/) [Neural](https://sms4smile.com/quotes/about/neural/) [Technology](https://sms4smile.com/quotes/about/technology/) [Vectors Think](https://sms4smile.com/quotes/about/vectors-think-4717976/) [Work](https://sms4smile.com/quotes/about/work/) ## Related quotes > [The paradigm for intelligence was logical reasoning, and the idea of what an internal representation would look like was it would be some kind…](https://sms4smile.com/quotes/geoffrey-hinton/the-paradigm-for-intelligence-was-logical-reasoning-and-the-idea-of/) [Geoffrey Hinton](https://sms4smile.com/quotes/author/geoffrey-hinton/) > [All you need is lots and lots of data and lots of information about what the right answer is, and you'll be able to…](https://sms4smile.com/quotes/geoffrey-hinton/all-you-need-is-lots-and-lots-of-data-and-lots-of-information-about/) [Geoffrey Hinton](https://sms4smile.com/quotes/author/geoffrey-hinton/) > [Everybody right now, they look at the current technology, and they think, 'OK, that's what artificial neural nets are.' And they don't realize how…](https://sms4smile.com/quotes/geoffrey-hinton/everybody-right-now-they-look-at-the-current-technology-and-they/) [Geoffrey Hinton](https://sms4smile.com/quotes/author/geoffrey-hinton/) > [The question is, can we make neural networks that are 1,000 times bigger? And how can we do that with existing computation?](https://sms4smile.com/quotes/geoffrey-hinton/the-question-is-can-we-make-neural-networks-that-are-1-000-times/) [Geoffrey Hinton](https://sms4smile.com/quotes/author/geoffrey-hinton/) > [Once your computer is pretending to be a neural net, you get it to be able to do a particular task by just showing…](https://sms4smile.com/quotes/geoffrey-hinton/once-your-computer-is-pretending-to-be-a-neural-net-you-get-it-to-be/) [Geoffrey Hinton](https://sms4smile.com/quotes/author/geoffrey-hinton/) > [I had a stormy graduate career, where every week we would have a shouting match. I kept doing deals where I would say, 'Okay,…](https://sms4smile.com/quotes/geoffrey-hinton/i-had-a-stormy-graduate-career-where-every-week-we-would-have-a/) [Geoffrey Hinton](https://sms4smile.com/quotes/author/geoffrey-hinton/) > [The pooling operation used in convolutional neural networks is a big mistake, and the fact that it works so well is a disaster.](https://sms4smile.com/quotes/geoffrey-hinton/the-pooling-operation-used-in-convolutional-neural-networks-is-a-big/) [Geoffrey Hinton](https://sms4smile.com/quotes/author/geoffrey-hinton/) > [I get very excited when we discover a way of making neural networks better - and when that's closely related to how the brain…](https://sms4smile.com/quotes/geoffrey-hinton/i-get-very-excited-when-we-discover-a-way-of-making-neural-networks/) [Geoffrey Hinton](https://sms4smile.com/quotes/author/geoffrey-hinton/) > [My main interest is in trying to find radically different kinds of neural nets.](https://sms4smile.com/quotes/geoffrey-hinton/my-main-interest-is-in-trying-to-find-radically-different-kinds-of/) [Geoffrey Hinton](https://sms4smile.com/quotes/author/geoffrey-hinton/) > [“There are an estimated 100 billion neurons residing inside the skull with an exponential amount of neural connections”](https://sms4smile.com/quotes/michio-kaku/there-are-an-estimated-100-billion-neurons-residing-inside-the-skull/) [Michio Kaku](https://sms4smile.com/quotes/author/michio-kaku/) > [I think the first wave of deep learning progress was mainly big companies with a ton of data training very large neural networks, right?…](https://sms4smile.com/quotes/andrew-ng/i-think-the-first-wave-of-deep-learning-progress-was-mainly-big/) [Andrew Ng](https://sms4smile.com/quotes/author/andrew-ng/) > [I'm a geek through and through. My last job at Microsoft was leading much of the search engine relevance work on Bing. There we…](https://sms4smile.com/quotes/ramez-naam/i-m-a-geek-through-and-through-my-last-job-at-microsoft-was-leading/) [Ramez Naam](https://sms4smile.com/quotes/author/ramez-naam/) > [Innate mechanisms endow the visual system with highly specific connections, but visual experience early in life is necessary for their maintenance and full development.…](https://sms4smile.com/quotes/torsten-wiesel/innate-mechanisms-endow-the-visual-system-with-highly-specific/) [Torsten Wiesel](https://sms4smile.com/quotes/author/torsten-wiesel/) > [“And what is the connection between Us and Them, how many bundled links do we find in the neural labyrinth? It's not enough to…](https://sms4smile.com/quotes/dom-delillo/and-what-is-the-connection-between-us-and-them-how-many-bundled-links/) [Dom DeLillo](https://sms4smile.com/quotes/author/dom-delillo/) > [Having been trained as a computer scientist in the '90s, everybody knew that AI didn't work. People tried it. They tried neural nets, and…](https://sms4smile.com/quotes/sergey-brin/having-been-trained-as-a-computer-scientist-in-the-90s-everybody-knew/) [Sergey Brin](https://sms4smile.com/quotes/author/sergey-brin/) ## More by Geoffrey Hinton > [I think the way we're doing computer vision is just wrong.](https://sms4smile.com/quotes/geoffrey-hinton/i-think-the-way-we-re-doing-computer-vision-is-just-wrong/) [Geoffrey Hinton](https://sms4smile.com/quotes/author/geoffrey-hinton/) > [Irony is going to be hard to get. You have to be master of the literal first. But then, Americans don't get irony either.…](https://sms4smile.com/quotes/geoffrey-hinton/irony-is-going-to-be-hard-to-get-you-have-to-be-master-of-the-literal/) [Geoffrey Hinton](https://sms4smile.com/quotes/author/geoffrey-hinton/) > [My main interest is in trying to find radically different kinds of neural nets.](https://sms4smile.com/quotes/geoffrey-hinton/my-main-interest-is-in-trying-to-find-radically-different-kinds-of/) [Geoffrey Hinton](https://sms4smile.com/quotes/author/geoffrey-hinton/) > [A deep-learning system doesn't have any explanatory power.](https://sms4smile.com/quotes/geoffrey-hinton/a-deep-learning-system-doesn-t-have-any-explanatory-power/) [Geoffrey Hinton](https://sms4smile.com/quotes/author/geoffrey-hinton/) > [We want to take AI and CIFAR to wonderful new places, where no person, no student, no program has gone before.](https://sms4smile.com/quotes/geoffrey-hinton/we-want-to-take-ai-and-cifar-to-wonderful-new-places-where-no-person/) [Geoffrey Hinton](https://sms4smile.com/quotes/author/geoffrey-hinton/) > [In deep learning, the algorithms we use now are versions of the algorithms we were developing in the 1980s, the 1990s. People were very…](https://sms4smile.com/quotes/geoffrey-hinton/in-deep-learning-the-algorithms-we-use-now-are-versions-of-the/) [Geoffrey Hinton](https://sms4smile.com/quotes/author/geoffrey-hinton/) > [Computers will understand sarcasm before Americans do.](https://sms4smile.com/quotes/geoffrey-hinton/computers-will-understand-sarcasm-before-americans-do/) [Geoffrey Hinton](https://sms4smile.com/quotes/author/geoffrey-hinton/) > [The role of radiologists will evolve from doing perceptual things that could probably be done by a highly trained pigeon to doing far more…](https://sms4smile.com/quotes/geoffrey-hinton/the-role-of-radiologists-will-evolve-from-doing-perceptual-things/) [Geoffrey Hinton](https://sms4smile.com/quotes/author/geoffrey-hinton/) > [I get very excited when we discover a way of making neural networks better - and when that's closely related to how the brain…](https://sms4smile.com/quotes/geoffrey-hinton/i-get-very-excited-when-we-discover-a-way-of-making-neural-networks/) [Geoffrey Hinton](https://sms4smile.com/quotes/author/geoffrey-hinton/) > [Deep learning is already working in Google search and in image search; it allows you to image-search a term like 'hug.' It's used to…](https://sms4smile.com/quotes/geoffrey-hinton/deep-learning-is-already-working-in-google-search-and-in-image-search/) [Geoffrey Hinton](https://sms4smile.com/quotes/author/geoffrey-hinton/) > [In A.I., the holy grail was how do you generate internal representations.](https://sms4smile.com/quotes/geoffrey-hinton/in-a-i-the-holy-grail-was-how-do-you-generate-internal-representations/) [Geoffrey Hinton](https://sms4smile.com/quotes/author/geoffrey-hinton/) > [As soon as you have good mechanical technology, you can make things like backhoes that can dig holes in the road. But of course…](https://sms4smile.com/quotes/geoffrey-hinton/as-soon-as-you-have-good-mechanical-technology-you-can-make-things/) [Geoffrey Hinton](https://sms4smile.com/quotes/author/geoffrey-hinton/) > [To deal with a 14-dimensional space, visualize a 3-D space and say 'fourteen' to yourself very loudly. Everyone does it.](https://sms4smile.com/quotes/geoffrey-hinton/to-deal-with-a-14-dimensional-space-visualize-a-3-d-space-and-say/) [Geoffrey Hinton](https://sms4smile.com/quotes/author/geoffrey-hinton/) > [In science, you can say things that seem crazy, but in the long run, they can turn out to be right. We can get…](https://sms4smile.com/quotes/geoffrey-hinton/in-science-you-can-say-things-that-seem-crazy-but-in-the-long-run/) [Geoffrey Hinton](https://sms4smile.com/quotes/author/geoffrey-hinton/) > [My view is we should be doing everything we can to come up with ways of exploiting the current technology effectively.](https://sms4smile.com/quotes/geoffrey-hinton/my-view-is-we-should-be-doing-everything-we-can-to-come-up-with-ways/) [Geoffrey Hinton](https://sms4smile.com/quotes/author/geoffrey-hinton/) [Explore all 52 Geoffrey Hinton quotes ](https://sms4smile.com/quotes/author/geoffrey-hinton/) ## More Everything quotes > [This may sound strange, but although I feel like I know everything about my characters, the brand of shampoo they use, how many cavities…](https://sms4smile.com/quotes/gail-honeyman/this-may-sound-strange-but-although-i-feel-like-i-know-everything/) [Gail Honeyman](https://sms4smile.com/quotes/author/gail-honeyman/) > [My parents were not musical, and they were not effervescent people; everything was very quiet. The music that I played was loud; it used…](https://sms4smile.com/quotes/don-mclean/my-parents-were-not-musical-and-they-were-not-effervescent-people/) [Don McLean](https://sms4smile.com/quotes/author/don-mclean/) > [If you think you're doing everything right, then you have a tendency to stand pat.](https://sms4smile.com/quotes/john-stockton/if-you-think-you-re-doing-everything-right-then-you-have-a-tendency/) [John Stockton](https://sms4smile.com/quotes/author/john-stockton/) > [The Fringe is by far my favorite time of year; I like everything about it. But there are people I know who are much…](https://sms4smile.com/quotes/alex-horne/the-fringe-is-by-far-my-favorite-time-of-year-i-like-everything-about/) [Alex Horne](https://sms4smile.com/quotes/author/alex-horne/) > [You can't force people to feel in a certain way, and the sooner you understand that,the better. I feel everything has its way of…](https://sms4smile.com/quotes/sidharth-malhotra/you-can-t-force-people-to-feel-in-a-certain-way-and-the-sooner-you/) [Sidharth Malhotra](https://sms4smile.com/quotes/author/sidharth-malhotra/) > [Of everything I have done, 'The Archers' always gets the most excitement; there's a sort of uncontrollable joy from fans of the program.](https://sms4smile.com/quotes/felicity-jones/of-everything-i-have-done-the-archers-always-gets-the-most-excitement/) [Felicity Jones](https://sms4smile.com/quotes/author/felicity-jones/) > [It's very easy to fool yourself that you're working, you know, when you're really not working very hard. I mean, I'm very lazy. So…](https://sms4smile.com/quotes/robert-caro/it-s-very-easy-to-fool-yourself-that-you-re-working-you-know-when-you/) [Robert Caro](https://sms4smile.com/quotes/author/robert-caro/) > [Whether it was Little League or playing with your brothers or sisters, that was always a problem. If I would lose - because I…](https://sms4smile.com/quotes/cal-ripken-jr/whether-it-was-little-league-or-playing-with-your-brothers-or-sisters/) [Cal Ripken, Jr](https://sms4smile.com/quotes/author/cal-ripken-jr/) > [That's one of my idols, I really look up to Pacquiao. This guy is everything I would want to be.](https://sms4smile.com/quotes/ryan-garcia/that-s-one-of-my-idols-i-really-look-up-to-pacquiao-this-guy-is/) [Ryan Garcia](https://sms4smile.com/quotes/author/ryan-garcia/) > [The talk shows in the States want celebrities, not authors. In France, it is different; writers are called upon to comment on everything. They…](https://sms4smile.com/quotes/edmund-white/the-talk-shows-in-the-states-want-celebrities-not-authors-in-france/) [Edmund White](https://sms4smile.com/quotes/author/edmund-white/) > [Everything I write is highly personal, but put in such a way that it's not dropping everything in someone's lap. Although sometimes I think…](https://sms4smile.com/quotes/jane-siberry/everything-i-write-is-highly-personal-but-put-in-such-a-way-that-it-s/) [Jane Siberry](https://sms4smile.com/quotes/author/jane-siberry/) > [Everything I have experienced and learned in football led me towards one day becoming a coach.](https://sms4smile.com/quotes/roberto-carlos/everything-i-have-experienced-and-learned-in-football-led-me-towards/) [Roberto Carlos](https://sms4smile.com/quotes/author/roberto-carlos/) > [It's funny, everything is so much easier when you do it yourself.](https://sms4smile.com/quotes/carine-roitfeld/it-s-funny-everything-is-so-much-easier-when-you-do-it-yourself/) [Carine Roitfeld](https://sms4smile.com/quotes/author/carine-roitfeld/) > [Everything affects hip-hop. The question is, how does it affect the money that corporations are going to invest to put out different kinds of…](https://sms4smile.com/quotes/will-i-am/everything-affects-hip-hop-the-question-is-how-does-it-affect-the/) [will.i.am](https://sms4smile.com/quotes/author/will-i-am/) > [If God is first, and you kind of center everything else around Him being the main focal point, you really can make decisions that…](https://sms4smile.com/quotes/aj-michalka/if-god-is-first-and-you-kind-of-center-everything-else-around-him/) [AJ Michalka](https://sms4smile.com/quotes/author/aj-michalka/) [Browse all 13,134 Everything quotes ](https://sms4smile.com/quotes/about/everything/) ```json { "@context": "https://schema.org", "@graph": [ { "@type": "Quotation", "text": "We now think of internal representation as great big vectors, and we do not think of logic as the paradigm for how to get things to work. We just think you can have these great big neural nets that learn, and so, instead of programming, you are just going to get them to learn everything.", "creator": { "@type": "Person", "name": "Geoffrey Hinton" }, "isPartOf": { "@id": "https://sms4smile.com/quotes/#website" }, "url": "https://sms4smile.com/quotes/geoffrey-hinton/we-now-think-of-internal-representation-as-great-big-vectors-and-we/", "about": { "@type": "Thing", "name": "Everything" }, "@id": "https://sms4smile.com/quotes/geoffrey-hinton/we-now-think-of-internal-representation-as-great-big-vectors-and-we/#quotation", "image": { "@type": "ImageObject", "@id": "https://sms4smile.com/quotes/i/787/geoffrey-hinton-12991_everything_we-now-think-of-internal-representation_2993740.jpg", "contentUrl": "https://sms4smile.com/quotes/i/787/geoffrey-hinton-12991_everything_we-now-think-of-internal-representation_2993740.jpg", "url": "https://sms4smile.com/quotes/i/787/geoffrey-hinton-12991_everything_we-now-think-of-internal-representation_2993740.jpg", "width": 1080, "height": 1080, "caption": "“We now think of internal representation as great big vectors, and we do not think of logic as the paradigm…” — Geoffrey Hinton", "creditText": "SMS4Smile Quotes", "creator": { "@id": "https://sms4smile.com/quotes/#organization" } } }, { "@type": "BreadcrumbList", "itemListElement": [ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://sms4smile.com/" }, { "@type": "ListItem", "position": 2, "name": "Quotes", "item": "https://sms4smile.com/quotes/" }, { "@type": "ListItem", "position": 3, "name": "Geoffrey Hinton", "item": "https://sms4smile.com/quotes/author/geoffrey-hinton/" }, { "@type": "ListItem", "position": 4, "name": "We now think of internal representation...", "item": "https://sms4smile.com/quotes/geoffrey-hinton/we-now-think-of-internal-representation-as-great-big-vectors-and-we/" } ], "@id": "https://sms4smile.com/quotes/geoffrey-hinton/we-now-think-of-internal-representation-as-great-big-vectors-and-we/#breadcrumb" }, { "@type": "WebSite", "@id": "https://sms4smile.com/quotes/#website", "name": "SMS4Smile Quotes", "url": "https://sms4smile.com/quotes/", "publisher": { "@id": "https://sms4smile.com/quotes/#organization" } }, { "@type": "Organization", "@id": "https://sms4smile.com/quotes/#organization", "name": "SMS4Smile Quotes", "url": "https://sms4smile.com/quotes/", "logo": { "@type": "ImageObject", "url": "https://sms4smile.com/quotes/wp-content/themes/sq/assets/icons/icon-512.png", "width": 512, "height": 512 } } ] } ```