|
14 |
DECISION TREES
The idea that artificial neural networks can be used to solve a wider spectrum of learning tasks than other techniques has led some pundits to hail ANN as the ultimate machine learning algorithm. While there is a strong case for this argument, this isn’t to say that ANN fits the bill as a silver bullet algorithm. In certain cases, neural networks fall short, and decision trees are held up as a popular counterargument.
The huge amount of input data and computational resources required to train a neural network is the first downside of any attempt to solve all machine learning problems using this technique. Neural network-based applications like Google's image recognition engine rely on millions of tagged examples ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access