Capacity of two-layer feedforward neural networks with binary weights
Graph Chatbot
Chat with Graph Search
Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.
DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.
We derive bounds on the expected loss for authenti-cation protocols in channels which are constrained due to noisyconditions and communication costs. This is motivated by anumber of authentication protocols, where at least some partof the authentication is ...
The backpropagation algorithm is widely used for training multilayer neural networks. In this publication the steepness of its activation functions is investigated. In specific, it is discussed that changing the steepness of the activation function is equi ...
Proper initialization is one of the most important prerequisites for fast convergence of feed-forward neural networks like high order and multilayer perceptrons. This publication aims at determining the optimal variance (or range) for the initial weights a ...
We propose a method that exploits pose information in order to improve object classification. A lot of research has focused in other strategies, such as engineering feature extractors, trying different classifiers and even using transfer learning. Here, we ...
Computing the partition function and the marginals of a global probability distribution are two important issues in any probabilistic inference problem. In a previous work, we presented sub-tree based upper and lower bounds on the partition function of a g ...
Ieee Service Center, 445 Hoes Lane, Po Box 1331, Piscataway, Nj 08855-1331 Usa2008
The capacity of a particular large Gaussian relay network is determined in the limit as the number of relays tends to infinity. Upper bounds are derived from cut-set arguments, and lower bounds follow from an argument involving uncoded transmission. It is ...
Institute of Electrical and Electronics Engineers2005
Quantization of the parameters of a Perceptron is a central problem in hardware implementation of neural networks using a numerical technology. A neural model with each weight limited to a small integer range will require little surface of silicon. Moreove ...
Given a locally uniform sample set P of a smooth surface S. We derive upper and lower bounds on the number k of nearest neighbors of a sample point p that have to be chosen from P such that this neighborhood contains all restricted Delaunay neighbors of p. ...
