Hot answers tagged

3

It seems easy for this to be sublinear growth or superlinear growth, depending on context. If we imagine the space of the complex AI as split into two parts--the context model and the content model (that is, information and structure that is expected to be shared across entries vs. information and structure that is local to particular entries), then ...


2

You have lots of choices in how to store a policy, depending on how you have built it - using which RL algorithm, and what kind of representation for states and actions. Tabular reinforcement learning algorithms lend themselves well to storage in a database table with an indexed state_id column and one or both action and value columns. This might be a good ...


1

If your game agent performs any kind of advance learning from self play or database of moves, that will generate parameters for some kind of model (e.g. a table of expected values, or neural network weights to select a preferred action). This is unavoidable, and if you want to re-use the results of that machine learning, you absolutely have to store the ...


1

I know it seems like a cop-out answer to every question on AI, but "it depends". For example, if the bulk of the storage space is storing learned concepts, and attributes of example entities, then it stands to reason that concepts and entities could be reused. In that scenario, learning from an additional 10G of text would use less storage than the ...


1

If I understand you correctly, you should check out Word2Vec. From Wikipedia: Word2vec is a group of related models that are used to produce word embeddings. These models are shallow, two-layer neural networks that are trained to reconstruct linguistic contexts of words. Word2vec takes as its input a large corpus of text and produces a high-...


1

I would think you could use a graph database, perhaps Neo4J or Titan or something of that nature. Or, if you want a simple file format, you could use one of the many formats that exist for representing graphs. You can find a list and overview of some of them here. Another option would be to store them in RDF using a triplestore like Jena.


1

One option is NeuroML, one of the goals of which is: To facilitate the exchange of complex neuronal models between researchers, allowing for greater transparency and accessibility of models In general, the matrices associated with large neural network models are likely to be sparse. Hence a 'homebrew' alternative to the above would be to use something ...


Only top voted, non community-wiki answers of a minimum length are eligible