From Hopfield networks to Boltzmann machines
ثبت نشده
چکیده
From Hoppeld networks to Boltzmann machines 17.1 The capacity of the Hoppeld network We will rst explore the information storage capabilities of a binary Hoppeld network which learns using the Hebb rule by considering the stability of just one bit of one of the desired patterns, assuming that the state of the network is set to that desired pattern x (n). We will assume that the patterns to be stored are randomly selected binary patterns, and we will evaluate the probability that the selected bit is stable.
منابع مشابه
Storkey Learning Rules for Hopfield Networks
We summarize the Storkey Learning Rules for the Hopfield Model, and evaluate performance relative to other learning rules. Hopfield Models are normally used for auto-association, and Storkey Learning Rules have been found to have good balance between local learning and capacity. In this paper we outline different learning rules and summarise capacity results. Hopfield networks are related to Bo...
متن کاملAdvances in Deep Learning
Deep neural networks have become increasingly more popular under the name of deep learning recently due to their success in challenging machine learning tasks. Although the popularity is mainly due to the recent successes, the history of neural networks goes as far back as 1958 when Rosenblatt presented a perceptron learning algorithm. Since then, various kinds of artificial neural networks hav...
متن کاملFoundations and Advances in Deep Learning
Aalto University, P.O. Box 11000, FI-00076 Aalto www.aalto.fi Author Kyunghyun Cho Name of the doctoral dissertation Foundations and Advances in Deep Learning Publisher Unit Department of Information and Computer Science Series Aalto University publication series DOCTORAL DISSERTATIONS 21/2014 Field of research Machine Learning Manuscript submitted 2 September 2013 Date of the defence 21 March ...
متن کاملStochastic Hopfield Network for Multi-user Detection
In this paper a novel multi-user receiver is introduced, which unites fast convergence of neural networks with the asymptotically global optimization power of stochastic algorithms (e.g. Boltzmann machines). The proposed method is capable to achieve a 1..2 dB gain in performance over the traditional Hopfield neural network, while only 2 or 3 times more iterations is needed, which still does not...
متن کاملOn the equivalence of Hopfield networks and Boltzmann Machines
A specific type of neural networks, the Restricted Boltzmann Machines (RBM), are implemented for classification and feature detection in machine learning. They are characterized by separate layers of visible and hidden units, which are able to learn efficiently a generative model of the observed data. We study a "hybrid" version of RBMs, in which hidden units are analog and visible units are bi...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 1997