Applications of machine learning in manufacturing
Machine learning is concerned with enabling computer programs automatically to improve their performance at some tasks through experience. Manufacturing is an area where the application of machine learning can be very fruitful. However, little has been published about the use of machine learning techniques in the manufacturing domain. This paper evaluates several machine learning techniques and examines applications in which they have been successfully deployed. Special attention is given to inductive learning which is among the most mature of the machine learning approaches currently available. The paper concludes with a summary of some of the key research issues in machine learning.
You are right. Machine learning techniques are domain dependent in the sense that there are no universal learning techniques that could be applied to arbitrary data. Machine learning techniques implicitly have different biases and therefore often have their own strengths when handling data sets with particular properties.
Can you give some examples of open problems in manufacturing that you think
can be solved by using the current machine learning techniques?
Thank you.
Hi Maria: I just noticed your question had not been answered. My apologies! I must confess that I am not aware of open problems in manufacturing that can be solved by current machine learning techniques. If I were, I would probably be famous for being the first to solve them! However, there are still many problems (in manufacturing and other fields) that cannot be handled by current machine learning techniques. Such problems are being studied around the world by groups including our own. Watch this space!
Just one question, why there are so many techniques (or algorithms in other word) available in ML? Is it because of all these techniques are problem dependent specific or some other reasons?
Thanks.