Riemannian metrics for neural networks I: feedforward networks
نویسندگان
چکیده
منابع مشابه
Riemannian metrics for neural networks I: feedforward networks
We describe four algorithms for neural network training, each adapted to different scalability constraints. These algorithms are mathematically principled and invariant under a number of transformations in data and network representation, from which performance is thus independent. These algorithms are obtained from the setting of differential geometry, and are based on either the natural gradi...
متن کاملRiemannian metrics for neural networks
We describe four algorithms for neural network training, each adapted to different scalability constraints. These algorithms are mathematically principled and invariant under a number of transformations in data and network representation, from which performance is thus independent. These algorithms are obtained from the setting of differential geometry, and are based on either the natural gradi...
متن کاملFeedforward Neural Networks
Here x is an input, y is a “label”, v ∈ Rd is a parameter vector, and f(x, y) ∈ Rd is a feature vector that corresponds to a representation of the pair (x, y). Log-linear models have the advantage that the feature vector f(x, y) can include essentially any features of the pair (x, y). However, these features are generally designed by hand, and in practice this is a limitation. It can be laborio...
متن کاملFeedforward Neural Networks
Feedforward neural networks have been used to perform classifications and to learn functional mappings. This paper compares human performance to feedforward neural networks using back propagation in generating functional relationships from limited data. Many business judgments are made in situations where decision makers are required to infer relationships porn partial, incomplete, and conflict...
متن کاملEvolving Neural Feedforward Networks
For many practical problem domains the use of neural networks has led to very satisfactory results. Nevertheless the choice of an appropriate, problem specific network architecture still remains a very poorly understood task. Given an actual problem, one can choose a few different architectures, train the chosen architectures a few times and finally select the architecturewith the best behaviou...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Information and Inference
سال: 2015
ISSN: 2049-8764,2049-8772
DOI: 10.1093/imaiai/iav006