Singular value decomposition (SVD) can be viewed as a method for unsupervised training of a network that associates two classes of events reciprocally by linear connections throug...
Traditional hop-by-hop dynamic routing makes inefficient use of network resources as it forwards packets along already congested shortest paths while uncongested longer paths may b...
Minsoo Lee, Xiaohui Ye, Dan Marconett, Samuel John...
We present a new approximate inference algorithm for Deep Boltzmann Machines (DBM's), a generative model with many layers of hidden variables. The algorithm learns a separate...
Motivated by the slow learning properties of multilayer perceptrons (MLPs) which utilize computationally intensive training algorithms, such as the backpropagation learning algorit...
We propose to study links between three important classification algorithms: Perceptrons, Multi-Layer Perceptrons (MLPs) and Support Vector Machines (SVMs). We first study ways to...