very difficult
Real world AI is difficult because hidden factors affect all data, and representation learning helps uncover those meaningful patterns that are hard to see/describe by hand.
3 Matching Annotations
- Last 7 days
-
www.deeplearningbook.org www.deeplearningbook.org
-
-
If logistic regression were given an MRI scan of the patient, rather thanthe doctor’s formalized report, it would not be able to make useful predictions.Individual pixels in an MRI scan have negligible correlation with any complicationsthat might occur during delivery
Logistic regression does not work for MRI images. This is where deep learning comes into play. As I am working in the field of medical imaging, the most common solution to use is convolutional neural networks (CNNs).
-
The true challenge to artificial intelligence proved to be solvingthe tasks that are easy for people to perform but hard for people to describeformally—problems that we solve intuitively, that feel automatic, like recognizingspoken words or faces in images
This shows that the tasks that are simple for us humans (like recognizing faces or understanding speech) are extremely difficult for machines to replicate, and the tasks that seem intellectually hard (like playing chess) are much easier for computers to handle. It's interesting because it suggests that what feels simple in our daily lives actually involves a lot of complex steps that come together.
-