Researchers at Oxford University are setting Google's artificial intelligence DeepMind loose on analyzing Hearthstone and Magic: The Gathering playing cards.
According to Kotaku, the AI analyzes card data such as resource cost and damage, and turns it into code that a machine can read.
Here's the abstract from the paper titled 'Latent Predictor Networks for Code Generation': "Many language generation tasks require the production of text conditioned on both structured and unstructured inputs. We present a novel neural network architecture which generates an output sequence conditioned on an arbitrary number of input functions. Crucially, our approach allows both the choice of conditioning context and the granularity of generation, for example characters or tokens, to be marginalised, thus permitting scalable and effective training.
Continue reading…
Continue reading...
According to Kotaku, the AI analyzes card data such as resource cost and damage, and turns it into code that a machine can read.
Here's the abstract from the paper titled 'Latent Predictor Networks for Code Generation': "Many language generation tasks require the production of text conditioned on both structured and unstructured inputs. We present a novel neural network architecture which generates an output sequence conditioned on an arbitrary number of input functions. Crucially, our approach allows both the choice of conditioning context and the granularity of generation, for example characters or tokens, to be marginalised, thus permitting scalable and effective training.
Continue reading…
Continue reading...