In this work, we propose an infinite restricted Boltzmann machine (RBM), whose maximum likelihood estimation (MLE) corresponds to a constrained convex optimization. We consider the Frank-Wolfe algorithm to solve the program, which provides a sparse solution that can be interpreted as inserting a hidden unit at each iteration, so that the optimization process takes the form of a sequence of finite models of increasing complexity. As a side benefit, this can be used to easily and efficiently identify an appropriate number of hidden units during the optimization. The resulting model can also be used as an initialization for typical state-of-the-art RBM training algorithms such as contrastive divergence, leading to models with consistently higher test likelihood than random initialization.

In this work, we propose a novel and surprisingly simple routing strategy called self-routing, where each capsule is routed independently by its subordinate routing network. Therefore, the agreement between capsules is not required anymore, but both poses and activations of upper-level capsules are obtained in a way similar to Mixture-of-Experts. Our experiments on CIFAR10, SVHN, and SmallNORB showthat the self-routing performs more robustly against white-box adversarial attacks and affine transformations, requiring less computation.

We introduce a principled approach for unsupervised structure learning of deep neural networks.

And we propose end-to-end training and testing algorithms for this new architecture. Compared to classical neural nets with softmax function as output activation, the surrogate with interpolating function as output activation combines advantages of both deep and manifold learning.

Howe updated 3] using isunkno internal predictions prediction) 4-7].

CP decomposition compresses an input tensor into a sum of rank-one components, and Tucker decomposition approximates an input tensor by a core tensor multiplied by matrices. To date, matrix and tensor decomposition has been extensively analyzed, and there are a number of variations of such decomposition (Kolda and Bader, 2009), where the common goal is to approximate a given tensor by a smaller number of components, or parameters,inanefficientmanner. However, despite the recent advances of decomposition techniques, a learning theory that can systematically define decomposition for any order tensors including vectors and matrices is still under development. Moreover, it is well known that CP and Tucker tensor decomposition include non-convex optimization and that the global convergence is not guaranteed.

Multi-layered distributed representation is believed to be the key ingredient of deep neural networks especially in cognitive tasks like computer vision.

As such, unimodal distributions cannot fully capture statistics of convolutional activations, which will limit performance of deep CNNs.

Neural Information Processing Systems http://nips.cc/