![]() But getting a sensible answer from them may not be all that straightforward, especially if they pretend they know more than they actually do.Technology is everywhere…? Technology is everything…? Technology Since algorithms can often be biased, it would be great if we could ask them “Why did you show me that ad?” or “Why did you decline my application?”. In fact, it seems to have learned to give explanations that are total lies - if it doesn’t know the color of something, it’ll answer “it’s a black and white photo so i can’t tell” without realizing that this excuse only works on an actual black and white photo. ![]() So I wouldn’t necessarily believe Visual Chatbot’s answer to my question about the zoo rocks thing. (The construction “Do have ?” seems to almost always result in a “yes”, so I can report that yes, bunnies do have spaceships and lightsabers.) The answer to “do bunnies fly?” is “no”, but the answer to “can bunnies fly?” is “yes”, so either the algorithm is answering a lot of these questions at random, or bunnies *can* fly but choose not to. Actually, it turns out that a lot depends on how you ask the question. ![]() Upon further questioning, however, it also decided that dogs also have horns, and birds do not fly. But it did have similar problems with goats in trees, and now I finally got to ask why. This particular algorithm didn’t have trouble with hallucinating sheep like some other algorithms I tested. Algorithms make mistakes all the time, or accidentally learn the wrong thing. If you ask it enough questions, could you get an idea of how it made its mistakes?Īn algorithm that can explain itself is really useful. (For the record, it thought the stick lying on dirt was “a bird is standing on a rock in the snow”) This means this bot always thinks it’s on the best safari ever. So even if there isn’t an animal there, it will be convinced there is. It may have never seen an image of just rocks, or a plain stick lying on dirt. (This turns out to be a major challenge for self-driving cars.) And given Visual Chatbot’s tendency to react to confusion by digging itself a deeper hole, this can lead to some pretty surreal interactions.Īnother thing about Visual Chatbot is that most of the images it’s been trained on have something in them - a bird, a person, an animal. The problem is that humans are very weird, and there are still many things it’s never seen. ![]() It can answer fairly involved questions about a lot of different things, and that’s impressive. Now, Visual Chatbot was indeed trained on a huge variety of images. When confused, it tends not to admit it.It is not prepared for images that aren’t like the images it saw in training.It was trained on a large but very specific set of images.However, there are a couple of interesting things to note about this algorithm. It’s a demo by a team of academic researchers that goes along with a recent machine learning research paper (and a challenge for anyone who’d like to improve on it), and its performance is pretty state-of-the-art, meant to demonstrate image recognition, language comprehension, and spatial awareness. There is a delightful algorithm called Visual Chatbot that will answer questions about any image it sees. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |