Technologies for platform-targeted machine learning

One or more non-transitory machine-readable storage media comprising a plurality of instructions stored thereon that, in response to execution by a computing device, cause the computing device to:

• generate a machine learning algorithm model indicative of a plurality of classes between which a user input is to be classified, wherein the user input is to be classified as being associated with a particular class based on an application of one or more features to the user input, and wherein each of the one or more features has an associated implementation cost indicative of a cost to perform on a target platform on which the corresponding feature is to be applied to the user input, wherein the model is based on a reduced feature set of the one or more features determined by a calculation of a correlation matrix of the one or more features and an identification of a set features of the one or more features exceeding a predefined correlation threshold;
• and
• translate the machine learning algorithm model into hardware code for execution on the target platform.

A method for platform-targeted machine learning, the method comprising:

• generating, by a computing device, a machine learning algorithm model indicative of a plurality of classes between which a user input is to be classified, wherein the user input is to be classified as being associated with a particular class based on an application of one or more features to the user input, and wherein each of the one or more features has an associated implementation cost indicative of a cost to perform on a target platform on which the corresponding feature is to be applied to the user input, wherein the model is based on a reduced feature set of the one or more features determined by calculating a correlation matrix of the one or more features and identifying a set features of the one or more features exceeding a predefined correlation threshold;
• and
• translating, by the computing device, the machine learning algorithm model into hardware code for execution on the target platform.