Tag
This paper introduces a formal definition of 'machine-learnable sets' based on bounded-complexity Boolean autoencoders that fix set elements, with experiments using Boolean threshold networks to demonstrate learnability for Rorschach patterns and wild sets.
This paper analyzes language generation in the limit, introducing a precision notion to study the recall-precision trade-off. It shows that allowing infinitely many hallucinations (with diminishing frequency) can increase recall when the adversary withholds much of the target language.