(Or “backpropagation”) A learning algorithm for modifying a feed-forward neural network which minimises a continuous “error function” or “objective function.” Back-propagation is a “gradient descent” method of training in that it uses gradient information to modify the network weights to decrease the value of the error function on subsequent tests of the inputs. Other gradient-based methods from numerical analysis can be used to train networks more efficiently.
Back-propagation makes use of a mathematical trick when the network is simulated on a digital computer, yielding in just two traversals of the network (once forward, and once back) both the difference between the desired and actual output, and the derivatives of this difference with respect to the connection weights.
- Back-seat driver
an automobile passenger who offers the driver unsolicited advice, warnings, criticism, etc., especially from the backseat. any person who, by means of criticism, unsolicited advice, or the like, interferes in affairs that are not his or her concern or responsibility. noun (informal) a passenger in a car who offers unwanted advice to the driver a […]
the practice of making a loud and effusive display of friendliness, cordiality, etc., as by slapping persons on the back. noun A demonstratively friendly person: Bob and Bill, they’re back-slappers (1924+)
the practice of making a loud and effusive display of friendliness, cordiality, etc., as by slapping persons on the back. to subject to backslapping. to engage in backslapping. a hearty slap on the back given as a token of affability or congratulation: The bridegroom received many a warm handshake and backslap. Historical Examples Only the […]
to attempt to discredit (a person) by underhanded means, as innuendo, accusation, or the like.