Method for training and operating an artificial neural network capable of multitasking, artificial neural network capable of multitasking, and device

A method for training an artificial neural network (ANN) capable of multitasking, the method comprising the following steps:

• providing a first path for a first information flow through the ANN, the first path coupling an input layer of the ANN with at least one task-spanning intermediate layer of the ANN, which is common to a plurality of tasks of the ANN that differ from one another, and the first path couples the at least one task-spanning intermediate layer with a respective task-specific ANN segment of each of the plurality of tasks differing from one another;
• providing first training data for training task-spanning parameters, which are common to the plurality of tasks of the ANN differing from one another, via the input layer and the first path;
• providing at least one task-specific second path for a second information flow through the ANN that differs from the first information flow, the second path (P2) coupling the input layer of the ANN with only a portion of the task-specific ANN segments of the plurality of tasks differing from one another;
• and
• supplying second training data for the training of task-specific parameters via the second path.

An artificial neural network (ANN) capable of multi-tasking, comprising:

• an input layer;
• a plurality of task-specific ANN segments, which are allocated to a plurality of differing tasks of the ANN;
• at least one task-spanning intermediate layer situated between the input layer and the plurality of task-specific ANN segments and includes a number of parameters that are usable in a task-spanning manner;
• a first path which couples the input layer via the at least one task-spanning intermediate layer with the plurality of task-specific ANN segments for a first information flow through the ANN;
• and
• at least one task-specific second path which couples the input layer with only a subset of the plurality of task-specific ANN segments for a task-specific second information flow through the ANN that differs from the first information flow.

A device having at least one artificial neural network (ANN) which is capable of multi-tasking, the ANN comprising:

• an input layer;
• a plurality of task-specific ANN segments, which are allocated to a plurality of differing tasks of the ANN;
• at least one task-spanning intermediate layer situated between the input layer and the plurality of task-specific ANN segments and includes a number of parameters that are usable in a task-spanning manner;
• a first path which couples the input layer via the at least one task-spanning intermediate layer with the plurality of task-specific ANN segments for a first information flow through the ANN;
• and
• at least one task-specific second path which couples the input layer with only a subset of the plurality of task-specific ANN segments for a task-specific second information flow through the ANN that differs from the first information flow.

A method for operating an artificial neural network (ANN) capable of multi-tasking, the method comprising the following steps:

• in a first phase, jointly training a plurality of tasks of the ANN that differ from one another by supplying first training data via a first path which allows for a first information flow through the ANN;
• in a second phase, training one of more of the plurality of tasks of the trained ANN;
• and
• in a third phase, adapting at least one of the plurality of tasks of the ANN by supplying second training data via a second path, which differs from the first path, which permits a second information flow through the ANN which differs from the first information flow, independently of at least a further task of the plurality of tasks.

A non-transitory machine-readable memory medium on which is stored a computer program including instructions for training an artificial neural network (ANN) capable of multitasking, the instructions, when executed by a computer, causing the computer to perform the following steps:

• providing a first path for a first information flow through the ANN, the first path coupling an input layer of the ANN with at least one task-spanning intermediate layer of the ANN, which is common to a plurality of tasks of the ANN that differ from one another, and the first path couples the at least one task-spanning intermediate layer with a respective task-specific ANN segment of each of the plurality of tasks differing from one another;
• providing first training data for training task-spanning parameters, which are common to the plurality of tasks of the ANN differing from one another, via the input layer and the first path;
• providing at least one task-specific second path for a second information flow through the ANN that differs from the first information flow, the second path (P2) coupling the input layer of the ANN with only a portion of the task-specific ANN segments of the plurality of tasks differing from one another;
• and
• supplying second training data for the training of task-specific parameters via the second path.

A non-transitory machine-readable memory medium on which is stored a computer program including instructions for operating an artificial neural network (ANN) capable of multi-tasking, the instruction, when executed by a computer, causing the computer to perform the following steps:

• in a first phase, jointly training a plurality of tasks of the ANN that differ from one another by supplying first training data via a first path which allows for a first information flow through the ANN;
• in a second phase, training one of more of the plurality of tasks of the trained ANN;
• and
• in a third phase, adapting at least one of the plurality of tasks of the ANN by supplying second training data via a second path, which differs from the first path, which permits a second information flow through the ANN which differs from the first information flow, independently of at least a further task of the plurality of tasks.