Abstract: A device and computer-implemented method for machine learning. The method includes: providing first and second classes; providing a first set of scene graphs including scene graphs of digital images that are incorrectly classified in the first class or the second class; providing a second set of scene graphs including scene graphs of digital images that are correctly classified with respect to the first class or the second class; determining, depending on the first set of scene graphs and the second set of scene graphs a rule that indicates that a presence of a first object and/or a second object in a digital image and/or a relation between the first object and the second object in the scene graph of the digital image results in that the classification of the digital image includes a misclassification of the digital image into the second class instead of the first class.

Abstract: A device and computer-implemented method for machine learning. The method includes: providing an input, in particular a digital image or a symbolic description of a graph, wherein the input includes a first node, a first name, a second node, and a second name, and an edge between the first node and the second node; determining, with a first model an expression that associates the edge with the first node and the second node; determining with a second model an expression that associates the first node with the first name and an expression that associates the second node with the second name; providing a question that includes the first name and the second name; determining, with a third model, depending on the question an expression that includes the first name and the second name, and determining an answer to the question depending on the expressions.

Abstract: A device and method for operating a machine. The method comprises providing a digital image, providing a structured representation of a question, predicting with an object detector and depending on at least a part of the digital image an area of the digital image wherein an object is depicted in the digital image, predicting with a classifier and depending on at least a part of the digital image within the area a first score indicating a likelihood that the object is of a first class and a second score indicating a likelihood that the object is of a second class, providing at least one attribute value for the first class, adding to an answer set programming program a first rule comprising the at least one attribute value of the first class and/or a first constraint comprising the at least one attribute value of the first class.

Abstract: A device and a method for solving an answer set programming program. The method includes receiving constant symbols and a set of rules for the constant symbols that comprises the constant symbols, wherein the answer set programming program is defined depending on the set of rules, determining a solution to the answer set programming program that comprises at least one of the constant symbols, determining a constraint depending on a cost for the solution, selecting in the solution at least one constant symbol, redetermining the solution as a result of an answer set programming program that is defined depending on the set of rules, and the constraint, wherein when solving the answer set programming program for redetermining the solution, the at least one constant symbol is treated as variable in the set of rules.

Abstract: Machine scheduling for executing a set of jobs of a task with a set of machines. The scheduling includes determining in a first iteration a first schedule that solves an optimization problem, the optimization problem is defined by a set of rules that assign the set of jobs to the set of machines, the first schedule maps each job to one machine of the set that is capable of processing this job, an execution of jobs assigned to a machine are scheduled to be finished in a machine span, and in a second iteration either determining a constraint for a machine span and determining a second schedule that solves the optimization problem for the set of jobs and the set of machines under the constraint, or determining a second schedule that solves the optimization problem for a sub-set of the set of jobs and of the set of machines.

Abstract: A method for training a control strategy with the aid of reinforcement learning. The method includes carrying out passes, in each pass, an action that is to be carried out being selected for each state of a sequence of states of an agent, for at least some of the states the particular action being selected by specifying a planning horizon that predefines a number of states, ascertaining multiple sequences of states, reachable from the particular state, using the predefined number of states, by applying an answer set programming solver to an answer set programming program which models the relationship between actions and the successor states that are reached by the actions, selecting the sequence that delivers the maximum return, and selecting an action as the action for the particular state via which the first state of the selected sequence may be reached, starting from the particular state.