While applications of deep learning have produced impressive empirical results, the theory behind it is still poorly developed. However, a team of researchers from Intel and the Hebrew University are saying that they have made an important breakthrough that allows for a better theoretical understanding of the capabilities of deep learning.
The study focused on the capability of deep learning to simulate quantum computing computations. According to the researchers, their findings indicate that the key element explaining the success of deep learning is how information is “reused” in two of the most successful neural network types, convolutional neural nets (CNNs) and recurrent neural networks (RNNs).
No comments:
Post a Comment