Mobile ai
AssigneeInternational Business Machines Corporation
InventorsUmar Asif, Stefan von Cavallar, Jianbin Tang, Stefan Harrer
Life of this patent
Estimating the term…
Abstract
A machine learning model can be optimized for deployment on a device based on hardware specifications of the device. An existing model is acquired and pruned to reduce hardware resource consumption of the model. The pruned model is then trained based on training data. The pruned model is also trained based on a collection of “teacher” models. Performance of the trained model is then evaluated and compared to performance requirements, which can be based on the hardware specifications of a device.
Claims20
A method of selecting a machine learning model comprising:
- receiving hardware specifications of a device;
- determining a performance requirement based on the hardware specifications of the device;
- acquiring a set of machine learning models, the set of machine learning models including:
- a first machine learning model having a first set of layers;
- and
- a teacher model;
- deleting one or more layers of the first set of layers from the first machine learning model, resulting in a student model with a pruned set of layers;
- training the student model based on:
- training data;
- and
- the teacher model;
- evaluating a performance of the student model;
- comparing the performance of the student model and the performance requirement;
- and
- determining, based at least on the comparing, to select a model having a highest performance.
A system, comprising:
- a memory;
- and
- a central processing unit (CPU) coupled to the memory, the CPU configured to execute instructions to:
- receive hardware specifications of a device;
- determine a performance requirement based on the hardware specifications;
- acquire a set of machine learning models, the set of machine learning models including:
- a first machine learning model having a first set of layers;
- and
- a teacher model;
- delete one or more layers of the first set of layers from the first machine learning model, resulting in a first student model having a first pruned set of layers;
- train the first student model based on:
- training data;
- and
- the teacher model;
- evaluate a performance of the first student model;
- compare the performance of the first student model to the performance requirement;
- and
- determine, based at least on the comparing, to generate a second student model.
A computer program product, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computer to cause the computer to:
- receive hardware specifications of a device;
- determine a performance requirement based on the hardware specifications of the device;
- acquire a set of machine learning models, the set of machine learning models including:
- a first machine learning model having a first set of layers;
- and
- a teacher model;
- delete one or more layers of the first set of layers from the first machine learning model, resulting in a student model with a pruned set of layers;
- train the student model based on:
- training data;
- and
- the teacher model;
- evaluate a performance of the student model;
- compare the performance of the student model and the performance requirement;
- and
- determine, based at least on the comparing, to select a model having a highest performance.
Dependencies are inferred from the claim text.