Abstract: Systems and methods for enriching datasets while learning are provided. For example, intermediate results of training machine learning algorithms may be obtained. Additional training examples may be selected based on the intermediate results. In some cases, synthetic examples may be generated based on the intermediate results. The machine learning algorithms may be further trained using the selected additional training examples and/or the generated synthetic examples.

Abstract: Systems and methods for personalized quality assurance of inference models are provided. For example, data items associated with a group of devices may be obtained, results of applying the data items to inference models may be obtained, the results of applying the data items to a first inference model may be compared with the results of applying the data items to a second inference model, and the compatibility of the second inference model to the group of devices may be assessed, for example based on the comparison results. In some examples, when the second inference model is found compatible, the second inference model may be utilized in tasks associated with the group of devices. In some examples, when the second inference model is found incompatible, the system may forgo the usage of the second inference model in one or more tasks associated with the group of devices.

Abstract: Systems and methods for personalized quality assurance of inference models are provided. For example, data items associated with a group of devices may be obtained, results of applying the data items to inference models may be obtained, the results of applying the data items to a first inference model may be compared with the results of applying the data items to a second inference model, and the compatibility of the second inference model to the group of devices may be assessed, for example based on the comparison results. In some examples, when the second inference model is found compatible, the second inference model may be utilized in tasks associated with the group of devices. In some examples, when the second inference model is found incompatible, the system may forgo the usage of the second inference model in one or more tasks associated with the group of devices.

Abstract: Systems and methods for estimating the required processing resources for machine learning tasks are provided. For example, properties of a machine learning training task may be obtained, properties of external devices may be obtained, and the processing resources requirements of the machine learning training task may be estimated (for example using the properties of the external devices). In some examples, the estimation may be provided to a user. In some examples, a group of devices may be selected, and the selected group of devices may be triggered to perform the machine learning training task.

Abstract: Systems and methods for enriching datasets while learning are provided. For example, intermediate results of training machine learning algorithms may be obtained. Additional training examples may be selected based on the intermediate results. In some cases, synthetic examples may be generated based on the intermediate results. The machine learning algorithms may be further trained using the selected additional training examples and/or the generated synthetic examples.