Transfer learning, photographs, and machine vision are all topics on this episode of The AI Minute. For more on Artificial Intelligence: https://voicesinai.com https://gigaom.com https://byronreese.com https://amzn.to/2vgENbn... Transcript: Humans are able to do something that machines are nowhere near able to emulate, something that is very critical to being able to advance the science of artificial intelligence. If you show a person a picture of something, a photograph of something, they can actually recognize the object even if the object within it is partially obscured, a photograph from a different angle where the lighting is changed, or where the object is under water or any other number of variations of ways to obscure it. Machines can't do anything like this. Machines actually need an enormous number of samples of things to train on. So how is it that humans are able to with just a sample size of 1, identify all kinds of variants of an object? Well it's because we have a lifetime of being able to look at objects in different amounts of light or underwater or under different conditions. And we are able to use those techniques effortlessly in this new environment. This is something called transfer learning, which machines are not able to do very well, but it's super important for getting more advances in the areas that we don't have nicely labeled data.
2019年4月24日星期三
Will Machines Master Transfer Learning?
Transfer learning, photographs, and machine vision are all topics on this episode of The AI Minute. For more on Artificial Intelligence: https://voicesinai.com https://gigaom.com https://byronreese.com https://amzn.to/2vgENbn... Transcript: Humans are able to do something that machines are nowhere near able to emulate, something that is very critical to being able to advance the science of artificial intelligence. If you show a person a picture of something, a photograph of something, they can actually recognize the object even if the object within it is partially obscured, a photograph from a different angle where the lighting is changed, or where the object is under water or any other number of variations of ways to obscure it. Machines can't do anything like this. Machines actually need an enormous number of samples of things to train on. So how is it that humans are able to with just a sample size of 1, identify all kinds of variants of an object? Well it's because we have a lifetime of being able to look at objects in different amounts of light or underwater or under different conditions. And we are able to use those techniques effortlessly in this new environment. This is something called transfer learning, which machines are not able to do very well, but it's super important for getting more advances in the areas that we don't have nicely labeled data.
订阅：
博文评论 (Atom)
没有评论:
发表评论