Is using a neural network preferable in anyway to just a traditional mathematical function if it works? I would assume that a traditional higher degree polynomial may be better due to the lower memory footprint.
pgupta31
It's so interesting to see the intersection between neural networks and this class! It's also cool to see how a simple linear classifier could be used for determining something like occupancy in a scene.
StevenChri
@adityaramkumar, this is just my perspective on your question, but I believe that traditional mathematical functions are too "simple" in the sense that we cannot accurately represent the complexities of objects/scenes we'd like to model. Not only that, but finding mathematical functions to best match these objects is a difficult task in itself. Therefore, I think these neural networks chip at that problem by steadily being able to better model the objects through rules, features and heuristics, examples of which are seen from this slide.
Is using a neural network preferable in anyway to just a traditional mathematical function if it works? I would assume that a traditional higher degree polynomial may be better due to the lower memory footprint.
It's so interesting to see the intersection between neural networks and this class! It's also cool to see how a simple linear classifier could be used for determining something like occupancy in a scene.
@adityaramkumar, this is just my perspective on your question, but I believe that traditional mathematical functions are too "simple" in the sense that we cannot accurately represent the complexities of objects/scenes we'd like to model. Not only that, but finding mathematical functions to best match these objects is a difficult task in itself. Therefore, I think these neural networks chip at that problem by steadily being able to better model the objects through rules, features and heuristics, examples of which are seen from this slide.