Making Sense out of Machine Learning and Deep Learning


[H]F Junkie
Apr 25, 2001
The good folks at AMD have published a page on Machine Learning and Deep Learning. It's a good read because it breaks down what many call AI and does it in an easily understood fashion. I've never really dug too deeply into the differences between ML and DL so this write-up was an eye-opener for me. I didn't realize that the primary difference between ML and DL is the representation of data. Also, it was interesting to learn DL is what's used in many of the AI applications we are used to seeing. If you want to get a deeper understanding of ML and DL you should take a look at what AMD has to say on the subject.

Today’s state-of-the-art ML and DL computer intelligence systems can adjust operations after continuous exposure to data and other input. While related in nature, subtle differences separate these fields of computer science.
Thank you for this- that write-up by AMD was quite succinct and did a great job of clarifying the difference between ML and DL from the perspective of data. Not sure if my memory serves well, but I recall other write-ups focusing more on the complexity of the network layers themselves.
It's kind of a strange to ask what's the difference between machine learning and deep learning when deep learning is a subset of machine learning.

edit: also, im confused. What they describe as the main difference between machine learning and deep learning sounds more like the difference between supervised and unsupervised machine learning. No?

edit edit: nvm, I see what they are saying. Typical machine learning requires an expert to decide what features to use from the data. Deep Learning usually has the system learn what features to use.
Last edited: