Abstract: Features related to systems and methods for automated generation of a machine learning model based in part on a pretrained model are described. The pretrained model is used as a starting point to augment and retrain according to client specifications. The identification of an appropriate pretrained model is based on the client specifications such as model inputs, model outputs, and similarities between the data used to train the models.

Abstract: Techniques are described automatically determining runtime configurations used to execute recurrent neural networks (RNNs) for training or inference. One such configuration involves determining whether to execute an RNN in a looped, or “rolled,” execution pattern or in a non-looped, or “unrolled,” execution pattern. Execution of an RNN using a rolled execution pattern generally consumes less memory resources than execution using an unrolled execution pattern, whereas execution of an RNN using an unrolled execution pattern typically executes faster. The configuration choice thus involves a time-memory tradeoff that can significantly affect the performance of the RNN execution. This determination is made automatically by a machine learning (ML) runtime by analyzing various factors such as, for example, a type of RNN being executed, the network structure of the RNN, characteristics of the input data to the RNN, an amount of computing resources available, and so forth.

Abstract: Features related to systems and methods for automated generation of a machine learning model based in part on a pretrained model are described. The pretrained model is used as a starting point to augment and retrain according to client specifications. The identification of an appropriate pretrained model is based on the client specifications such as model inputs, model outputs, and similarities between the data used to train the models.

Abstract: In one embodiment, one or more computing systems may determine a first set of bins that collectively cover a pre-determined numerical range with each bin covering a sub-range of the pre-determined range. The system may determine a second set of bins that collectively cover the pre-determined range with each covers a different but overlapping sub-range with respect to a corresponding bin in the first bin set. The system may access a value that falls within the pre-determined range. The system may determine that the value falls within a first bin of the first bin set and a second bin of the second bin set. The system may determine a positive value for each the first and second bins. The positive values indicate an association level of the value with the first and second bins. The system may determine a representation of the value based on the positive values.

Abstract: Techniques for model adaptation are described. For example, a method of receiving a call to provide either a model variant or a model variant profile of a deep learning model, the call including desired performance of the deep learning model, a deep learning model identifier, and current edge device characteristics; comparing the received current edge device characteristics to available model variants and profiles based on the desired performance of the deep learning model to generate or select a model variant or profile, the available model variants and profiles determined by the model identifier; and sending the generated or selected model variant or profile to the edge device to use in inference is detailed.

Abstract: Techniques for benchmarking a machine learning model/algorithm are described. For example, in some instances a method includes generating an execution plan for benchmarking of at least one task corresponding to a machine learning model based on an identified machine learning model, identified training data, and at least one objective for the benchmarking job; receiving execution statistics about the execution of the task as a part of the benchmarking job according to the execution plan; and updating the execution plan based at least in part on the received execution statistics of the task.

Abstract: Technology is described for directing media content to a target device. A media content directing request may be received from a source device indicating that the source device intends to direct media content to the target device that is available for media content playback. A list of available target devices for media content playback may be provided to the source device. A playback message may be received from the source device that includes a selection of the target device from the list of available target devices. Communication of the playback message to the target device may be facilitated to initiate playback of media content from a media content playback server as directed by the source device.