Appropriate Problems for ANN

• training data is noisy, complex sensor data
• also problems where symbolic algos are used (decision tree learning (DTL)) - ANN and DTL produce results of comparable accuracy
• instances are attribute-value pairs, attributes may be highly correlated or independent, values can be any real value
• target function may be discrete-valued, real-valued or a vector
• training examples may contain errors
• long training times are acceptable
• requires fast eval. of learned target func.
• humans do NOT need to understand the learned target func.