Constructive Training Methods for Feedforward Neural Networks with Binary Weights
Graph Chatbot
Chattez avec Graph Search
Posez n’importe quelle question sur les cours, conférences, exercices, recherches, actualités, etc. de l’EPFL ou essayez les exemples de questions ci-dessous.
AVERTISSEMENT : Le chatbot Graph n'est pas programmé pour fournir des réponses explicites ou catégoriques à vos questions. Il transforme plutôt vos questions en demandes API qui sont distribuées aux différents services informatiques officiellement administrés par l'EPFL. Son but est uniquement de collecter et de recommander des références pertinentes à des contenus que vous pouvez explorer pour vous aider à répondre à vos questions.
This report presents one month trainee work on development of French Automatic Speech Recognition ASR system using a french part of multilingual database GlobalPhone_FR. The purpose of this report is to explain and give results of the training and testing ...
We show that Hopfield neural networks with synchronous dynamics and asymmetric weights admit stable orbits that form sequences of maximal length. For N units, these sequences have length T = 2^N; that is, they cover the full state space. We present a mathe ...
Temporal integration of information and prediction of future sensory inputs are assumed to be important computational tasks of generic cortical microcircuits. It has remained open how cortical microcircuits could possibly achieve this, especially since the ...
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 ...
Previous work on statistical language modeling has shown that it is possible to train a feed-forward neural network to approximate probabilities over sequences of words, resulting in significant error reduction when compared to standard baseline models. Ho ...
Artificial neural networks represent a simple but efficient way to model and correct known errors existing between commonly used density functional computations and experimental data. The recently proposed X1 approach combines B3LYP energies with a neural- ...
A key challenge for neural modeling is to explain how a continuous stream of multimodal input from a rapidly changing environment can be processed by stereotypical recurrent circuits of integrate-and-fire neurons in real time. We propose a new computationa ...
In this paper we propose a method for classifying regions of images and videos frames into text and non-text regions using support vector machine (SVM). Different features are proposed to characterise the texture formed by text characters and background. S ...
In this paper we apply the Full Combination (FC) multi-band approach, which has originally been introduced in the framework of posterior-based HMM/ANN (Hidden Markov Model/Artificial Neural Network) hybrid systems, to systems in which the ANN (or Multilaye ...
How can we decipher the hidden structure of a network based on limited observations? This question arises in many scenarios ranging from social to wireless and to neural networks. In such settings, we typically observe the nodes’ behaviors (e.g., the time ...
