Constructing modular architectures with Boltzmann Machines
نویسنده
چکیده
In this paper, I discuss how the Boltzmann Machine framework can be used for modeling hybrid and modular architectures. The advantage is that it provides a rm theoretical basis for the derivation of learning rules in the presence of lateral inhibition, feed-forward and feedback .
منابع مشابه
Deep Learning using Restricted Boltzmann Machines
Restricted Boltzmann machines (RBM) are probabilistic graphical models which are represented as stochastic neural networks. Increase in computational capacity and development of faster learning algorithms, led RBMs to become more useful for many machine learning problems. RBMs are the building blocks of many deep multilayer architectures like Deep Belief networks (DBN) and Deep Boltzmann Machin...
متن کاملNotes on Boltzmann Machines
I. INTRODUCTION Boltzmann machines are probability distributions on high dimensional binary vectors which are analogous to Gaussian Markov Random Fields in that they are fully determined by first and second order moments. A key difference however is that augmenting Boltzmann machines with hidden variables enlarges the class of distributions that can be modeled, so that in principle it is possib...
متن کاملHybrid Parallelization Techniques for Lattice Boltzmann Free Surface Flows
In the following, we will present an algorithm to perform adaptive free surface simulations with the lattice Boltzmann method (LBM) on machines with shared and distributed memory architectures. Performance results for different test cases and architectures will be given. The algorithm for parallelization yields a high performance, and can be combined with the adaptive LBM simulations. Moreover,...
متن کاملOger: modular learning architectures for large-scale sequential processing
Oger (OrGanic Environment for Reservoir computing) is a Python toolbox for building, training and evaluating modular learning architectures on large data sets. It builds on MDP for its modularity, and adds processing of sequential data sets, gradient descent training, several crossvalidation schemes and parallel parameter optimization methods. Additionally, several learning algorithms are imple...
متن کاملOn representation learning for artificial bandwidth extension
Recently, sum-product networks (SPNs) showed convincing results on the ill-posed task of artificial bandwidth extension (ABE). However, SPNs are just one type of many architectures which can be summarized as representational models. In this paper, using ABE as benchmark task, we perform a comparative study of Gauss Bernoulli restricted Boltzmann machines, conditional restricted Boltzmann machin...
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 2007