Learning coach for machine learning system
AssigneeD5Ai LLC
InventorJames K. Baker
Life of this patent
Estimating the term…
Abstract
A machine learning system includes a coach machine learning system that uses machine learning to help a student machine learning system learn its system. By monitoring the student learning system, the coach machine learning system can learn (through machine learning techniques) “hyperparameters” for the student learning system that control the machine learning process for the student learning system. The machine learning coach could also determine structural modifications for the student learning system architecture. The learning coach can also control data flow to the student learning system.
Claims55
A machine learning (ML) computer system for training a student ML system iteratively through machine learning on training data to perform a machine learning task, wherein the student ML system comprises:
- an input layer, an output layer, and at least a first inner layer between the input and output layers;
- each layer comprises at least one node, such that the first inner layer comprises at least a first node;
- the first node of the first inner layer outputs an activation value for each set of input values to the first node of the first inner layer;
- the activation value is determined based on an activation function for the first node of the first inner layer and based on learned parameters for the first node of the first inner layer;
- and
- following iterations of training of the student ML system, the learned parameters for the first node of the first inner layer are updated, and
- the ML computer system comprises a learning coach ML system that is in communication with the student ML system, wherein:
- the learning coach ML system comprises a neural network that comprises an input layer and an output layer;
- the learning coach ML system has been trained through machine learning to determine and implement an enhancement to the student ML system based on input to the learning coach ML system from the student ML system, wherein the input from the student ML system is input to the input layer of the learning coach ML system;
- the input to the learning coach ML system from the student ML system comprises observations about an internal state of the student ML system during training of the student ML system;
- and
- the observations about the internal state of the student ML system comprise values related to the learned parameters for the first node on the first inner layer of the student ML system and the activation values for the first node on the first inner layer of the student ML system,
- such that the learning coach ML system determines and implements the enhancement to the student ML system based on the input from the student ML system.
A machine-learning (ML) training method comprising:
- initially training a learning coach ML system to determine and implement an enhancement to a ML system, wherein the learning coach ML system comprises an input layer and an output layer;
- training, iteratively through machine learning, a student ML system on training data to perform a machine learning task, wherein:
- the student ML system comprises an input layer, an output layer, and at least a first inner layer between the input and output layers;
- each layer comprises at least one node, such that the first inner layer comprises at least a first node;
- the first node of the first inner layer outputs an activation value for each set of input values to the first node of the first inner layer;
- the activation value is determined based on an activation function for the first node of the first inner layer and based on learned parameters for the first node of the first inner layer;
- and
- the initial training the student ML system comprises, following iterations of the training of the student ML system, updating the learned parameters for the first node of the first inner layer;
- and
- training the student ML system comprises:
- receiving, by the learning coach ML system, from the student ML system, values related to the learned parameters and the activation values of the first node of the first inner layer of the student ML system;
- and
- determining and implementing, by the learning coach ML system, the enhancement to the student ML system based on the values related to the learned parameters and the activation values of the first node of the inner layer of the student ML system to improve performance of the student ML system.
Dependencies are inferred from the claim text.