On-the-fly deep learning in machine learning at autonomous machines

A method comprising:

• extracting, by one or more general-purpose graphics processors of a data processing system, a feature learned by a first deep neural network (DNN) model, wherein the first DNN model is a pre-trained DNN model for computer vision to enable context-independent classification of an object within an input video frame, instructions executed by the general-purpose processor to extract the feature are provided via a deep learning framework, the deep learning framework is provided by a graphics execution environment on a server computing device, and the deep learning framework provides instructions to accelerate deep learning operations;
• and
• training, via the deep learning framework, a second DNN model for computer vision based on the extracted feature, the second DNN model an update of the first DNN model, wherein training the second DNN model includes training the second DNN model based on a dataset including context-dependent data.

A non-transitory machine-readable medium storing instructions which, when executed by one or more processors including one or more general-purpose graphics processors, cause the one or more processors to perform operations comprising:

• extracting, by the one or more general-purpose graphics processors, a feature learned by a first deep neural network (DNN) model, wherein the first DNN model is a pre-trained DNN model for computer vision to enable context-independent classification of an object within an input video frame, the instructions executed by the general-purpose processor to extract the feature are provided via a deep learning framework, the deep learning framework is provided by a graphics execution environment on a server computing device, and the deep learning framework provides instructions to accelerate deep learning operations;
• and
• training, via the deep learning framework, a second DNN model for computer vision based on the extracted feature, the second DNN model an update of the first DNN model, wherein training the second DNN model includes training the second DNN model based on a dataset including context-dependent data.

An apparatus comprising:

• first logic, as facilitated by or at least partially incorporated into a processor, to extract a feature learned by a first deep neural network (DNN) model, wherein the first DNN model is a pre-trained DNN model for computer vision to enable context-independent classification of an object within an input video frame;
• and
• second logic to train a second DNN model for computer vision based on the extracted feature, the second DNN model an update of the first DNN model, wherein training the second DNN model includes training the second DNN model based on a dataset including context-dependent data.