Artificial intelligence engine hosted on an online platform

Patent metadata

Field	Value
Publication number	US-11100423-B2
Application number	US-201715416970-A
Country	US
Kind code	B2
Filing date	Jan 26, 2017
Priority date	Jan 27, 2016
Publication date	Aug 24, 2021
Grant date	Aug 24, 2021

Abstract

Provided herein in some embodiments is an artificial intelligence (“AI”) engine hosted on one or more remote servers configured to cooperate with one or more databases including one or more AI-engine modules and one or more server-side client-server interfaces. The one or more AI-engine modules include an instructor module and a learner module configured to train an AI model. An assembly code can be generated from a source code written in a pedagogical programming language describing a mental model of one or more concept modules to be learned by the AI model and curricula of one or more lessons for training the AI model. The one or more server-side client-server interfaces can be configured to enable client interactions from a local client such as submitting the source code for training the AI model and using the trained AI model for one or more predictions.

First claim

What is claimed is:

1. An artificial intelligence (“AI”) engine hosted on one or more remote servers configured to cooperate with one or more databases, comprising:
one or more AI-engine modules including
an architect module,
an instructor module, and
a learner module,
wherein the architect module is configured to propose an AI model from an assembly code, and
wherein the instructor module and the learner module are configured to train the AI model in one or more training cycles with training data from one or more training data sources,
wherein the AI engine is configured to operate in a training mode or a predicting mode during the one or more training cycles,
wherein, in the training mode, the instructor module and the learner module are configured to:
i) instantiate the AI model conforming to the AI model proposed by the architect module, and
ii) train the AI model with a curricula of one or more lessons, and

wherein, in the predicting mode, a predictor AI-engine module is configured to: i) instantiate and execute the trained AI model on the training data for the one or more predictions in the predicting mode;
wherein the assembly code is generated from a source code written in a pedagogical programming language,
wherein the source code includes
a mental model of one or more concept modules to be learned by the AI model using the training data and
the curricula of the one or more lessons for training the AI model on the one or more concept modules, and

wherein the AI engine is configured to instantiate the trained AI model based on the one or more concept modules learned by the AI model in the one or more training cycles; and

one or more server-side client-server interfaces configured to enable client interactions with the AI engine in one or both client interactions selected from
submitting the source code for training the AI model and
using the trained AI model for one or more predictions based upon the training data
wherein the learner module and the instructor module are configured to pick out the curricula of the one or more lessons, thereby significantly cutting down on training time, memory, and computing cycles used by the AI engine for training the AI model.

2. The AI engine of claim 1 ,
wherein the one or more server-side client-server interfaces are configured to cooperate with one or more client-side client-server interfaces selected from a command-line interface, a graphical interface, a web-based interface, or a combination thereof.

3. The AI engine of claim 1 , further comprising
a compiler configured to generate the assembly code from the source code; and
a training data manager configured to push or pull the training data from one or more training data sources selected from a simulator, a training data generator, a training data database, or a combination thereof.

4. The AI engine of claim 1 ,
wherein the AI engine is configured to heuristically pick an appropriate learning algorithm from a plurality of machine learning algorithms in the one or more databases for training the AI model proposed by the architect module.

5. The AI engine of claim 4 ,
wherein the architect module is configured to propose one or more additional AI models,
wherein the AI engine is configured to heuristically pick an appropriate learning algorithm from the plurality of machine learning algorithms in the one or more databases for each of the one or more additional AI models,
wherein the instructor module and the learner module are configured to train the AI models in parallel,
wherein the one or more additional AI models are also trained in one or more training cycles with the training data from one or more training data sources,
wherein the AI engine is configured to instantiate one or more additional trained AI models based on the concept modules learned by the one or more AI models in the one or more training cycles, and
wherein the AI engine is configured to identify a best trained AI model among the trained AI models.

6. The AI engine of claim 5 , further comprising:
a trained AI-engine AI model,
wherein the trained AI-engine AI model provides enabling AI for proposing the AI models from the assembly code and picking the appropriate learning algorithms from the plurality of machine learning algorithms in the one or more databases for training the AI models, and
wherein the AI engine is configured to continuously train the trained AI-engine AI model in providing the enabling AI for proposing the AI models and picking the appropriate learning algorithms.

7. The AI engine of claim 5 , further comprising:
a meta-learning module configured to keep a record in the one or more databases for
i) the source code processed by the AI engine,
ii) mental models of the source code,
iii) the training data used for training the AI models,
iv) the trained AI models,
v) how quickly the trained AI models were trained to a sufficient level of accuracy, and
vi) how accurate the trained AI models became in making predictions on the training data.

8. The AI engine of claim 1 ,
wherein the AI engine is configured to make determinations regarding
i) when to train the AI model on each of the one or more concept modules and
ii) how extensively to train the AI model on each of the one or more concept modules, and

wherein the determinations are based on a relevance of each of the one or more concept modules in one or more predictions of the trained AI model based upon the training data.

9. The AI engine of claim 1 ,
wherein the AI engine is configured to provide one or more training status updates on training the AI model selected from
i) an estimation of a proportion of a training plan completed for the AI model,
ii) an estimation of a completion time for completing the training plan,
iii) the one or more concept modules upon which the AI model is actively training,
iv) mastery of the AI model on learning the one or more concept modules,
v) fine-grained accuracy and performance of the AI model on learning the one or more concept modules, and
vi) overall accuracy and performance of the AI model on learning one or more mental models.

10. A method for an artificial intelligence (“AI”) engine hosted on one or more remote servers configured to cooperate with one or more databases, comprising:
proposing an AI model,
wherein the AI engine includes an architect AI-engine module for proposing the AI model from an assembly code;
training the AI model,
wherein the AI engine includes an instructor AI-engine module and a learner AI-engine module for training the AI model in one or more training cycles with training data from one or more training data sources;
wherein the AI engine is configured to operate in a training mode or a predicting mode during the one or more training cycles,
wherein, in the training mode, the instructor AI-engine module and the learner AI-engine module are configured to:
i) instantiate the AI model conforming to the AI model proposed by the architect AI-engine module, and
ii) train the AI model with a curricula of one or more lessons, and

wherein, in the predicting mode, a predictor AI-engine module is configured to: i) instantiate and execute the trained AI model on the training data for the one or more predictions in the predicting mode;
compiling the assembly code from a source code,
wherein a compiler is configured to generate the assembly code from the source code written in a pedagogical programming language,
wherein the source code includes
a mental model of one or more concept modules to be learned by the AI model using the training data and
the curricula of one or more lessons for training the AI model on the one o

Assignees

• Microsoft Technology Licensing Llc

Inventors

• Hammond Mark Isaac
• Browne Keen Mcewan
• Campos Marcos
• Brown Matthew James
• Kong Ruofan
• Adams Megan

Classifications

• G06F8/31 Primary

  Programming languages or programming paradigms · CPC title

• G06N20/00 Primary

  Machine learning · CPC title

• G06F18/2148

  characterised by the process organisation or structure, e.g. boosting cascade · CPC title

• G06N3/096

  Transfer learning · CPC title

• G06N3/0985

  Hyperparameter optimisation; Meta-learning; Learning-to-learn · CPC title