The memory capacity of any quantum neural network is at most the information content of its trainable parameters, so classically-parameterized QNNs lack capacity advantage over classical NNs.
A Practical Approach to Sizing Neural Networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Memorization is worst-case generalization. Based on MacKay's information theoretic model of supervised machine learning, this article discusses how to practically estimate the maximum size of a neural network given a training data set. First, we present four easily applicable rules to analytically determine the capacity of neural network architectures. This allows the comparison of the efficiency of different network architectures independently of a task. Second, we introduce and experimentally validate a heuristic method to estimate the neural network capacity requirement for a given dataset and labeling. This allows an estimate of the required size of a neural network for a given problem. We conclude the article with a discussion on the consequences of sizing the network wrongly, which includes both increased computation effort for training as well as reduced generalization capability.
fields
quant-ph 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
The Capacity of Quantum Neural Networks
The memory capacity of any quantum neural network is at most the information content of its trainable parameters, so classically-parameterized QNNs lack capacity advantage over classical NNs.