Transfer learning and domain adaptation using distributable data models
A system for transfer learning and domain adaptation using distributable data models is provided, comprising a network-connected distributable model configured to serve instances of a plurality of distributable models; and a directed computation graph module configured to receive at least an instance of at least one of the distributable models from the network-connected computing system, create a second dataset from machine learning performed by a transfer engine, train the instance of the distributable model with the second dataset, and generate an update report based at least in part by updates to the instance of the distributable model.
1. A system for transfer learning and domain adaptation using distributable data models, comprising:
a distributable model source comprising a memory, a processor, and a plurality of programming instructions stored in the memory thereof and operable on the processor thereof, wherein the programmable instructions, when operating on the processor, cause the processor to:
store a plurality of machine learning models;
produce a distributable model instance based at least in part on a machine learning model;
transmit the distributable model instance via a network;
a transfer engine comprising a memory, a processor, and a plurality of programming instructions stored in the memory thereof and operable on the processor thereof, wherein the programmable instructions, when operating on the processor, cause the processor to:
receive at least a distributable model instance from the model source;
apply a plurality of machine learning algorithms to at least a portion of the received instance of the distributable model;
receive a pre-trained data model;
incorporate at least a portion of the pre-trained data model into a partially-unsupervised machine learning process; and
apply the partially-unsupervised machine learning process to the distributable model instance; and
a directed computational graph engine comprising a memory, a processor, and a plurality of programming instructions stored in the memory thereof and operable on the processor thereof, wherein the programmable instructions, when operating on the processor, cause the processor to:
receive at least a distributable model instance from the model source;
create a second dataset from data stored in the memory based at least in part on transfer learning performed by the transfer engine;
train the distributable model instance with the second dataset; and
generate an update report based at least in part by updates to the distributable model instance.
2. The system of claim 1 , wherein a machine learning algorithm comprises a probabilistic learning network.
3. The system of claim 2 , wherein the probabilistic learning network comprises a Markov logic network.
4. The system of claim 2 , wherein the probabilistic learning network comprises a Bayesian network.
5. A method for transfer learning and domain adaptation using distributable data models, comprising the steps of:
(a) storing, in a distributable model source, a plurality of machine learning models;
(b) producing a distributable model instance based at least in part on a machine learning model;
(c) transmitting the distributable model instance via a network;
(d) receiving, at a transfer engine, at least a distributable model instance from the distributable model source;
(e) applying a plurality of machine learning algorithms to the distributable model instance;
(f) using a directed computational graph engine to train the distributable model instance with the plurality of machine learning algorithms performed by the transfer engine;
(g) receiving a pre-trained data model;
(h) incorporating at least a portion of the pre-trained data model into a partially-unsupervised machine learning process;
(i) applying the partially-unsupervised machine learning process to the distributable model instance; and
(j) generating an update report based at least in part by updates to the distributable model instance.
6. The method of claim 5 , wherein a machine learning algorithm comprises a probabilistic learning network.
7. The method of claim 6 , wherein the probabilistic learning network comprises a Markov logic network.
8. The method of claim 6 , wherein the probabilistic learning network comprises a Bayesian network.