AIMC Topic: Concept Formation

Clear Filters Showing 41 to 43 of 43 articles

Human-level concept learning through probabilistic program induction.

Science (New York, N.Y.)
People learning new concepts can often generalize successfully from just a single example, yet machine learning algorithms typically require tens or hundreds of examples to perform with similar accuracy. People can also use learned concepts in richer...

["Chemistry of Concepts”and “Historical Sense”. On Philosophical Concept Formation].

Berichte zur Wissenschaftsgeschichte
"Chemistry of Concepts" and "Historical Sense". On Philosophical Concept Formation. The question concerning concepts and their relations to objects and words has had a long and controversial history. Recently, it is challenged by an anew turn towards...

Learning feature representations with a cost-relevant sparse autoencoder.

International journal of neural systems
There is an increasing interest in the machine learning community to automatically learn feature representations directly from the (unlabeled) data instead of using hand-designed features. The autoencoder is one method that can be used for this purpo...