Deep Learning with Deep Hybrid Feature Representations – Deep Neural Network (DNN) has emerged as a powerful tool for the analysis of neural network data. In this work, we explore deep learning-based methods to automatically segment neural networks based on their functional connectivity patterns. In this process, we consider the possibility to model the network structure of its neural network by analyzing the connectivity patterns on each module. We show that network structure is critical for segmentation of neural networks. The functional connectivity patterns on each module can be modeled by a weighted kernel which is a well known technique in the literature. We propose a method which integrates the functional connectivity patterns and the spatial information in each node by modeling the spatial network structure using functional connectivity functions. Our model-based approach is shown to have superior performance compared to a variety of network segmentation methods.

In this work we propose a new method for the dyadic dynamic modeling problem. Our main contribution is to compute the model parameters and the dynamics (for each dyadic variable) via a generalized Markov chain Monte Carlo (MCMC) algorithm. Based on the MCMC, the parameters of the model are modeled by a vector-valued model that can be learned using a simple graphical representation. The model is then evaluated using the dynamic model of the dyadic system according to an evaluation criterion that does not require the dynamical behavior of the dyadic system to be analyzed by the MCMC algorithm as it does not have any dependency on the dynamical properties of the dyadic system. We demonstrate the superiority of the proposed method via a detailed study on the dynamic model of the dyadic dynamic model.

Deep Learning for Improving Multi-Domain Image Retrieval

Stochastic, Stochastically Scalable, and Temporal ERC-SA Approaches to Energy Allocation Problems

Deep Learning with Deep Hybrid Feature Representations

Distributed Learning of Discrete Point Processes

On Theorem proving for the dyadic adaptive modelIn this work we propose a new method for the dyadic dynamic modeling problem. Our main contribution is to compute the model parameters and the dynamics (for each dyadic variable) via a generalized Markov chain Monte Carlo (MCMC) algorithm. Based on the MCMC, the parameters of the model are modeled by a vector-valued model that can be learned using a simple graphical representation. The model is then evaluated using the dynamic model of the dyadic system according to an evaluation criterion that does not require the dynamical behavior of the dyadic system to be analyzed by the MCMC algorithm as it does not have any dependency on the dynamical properties of the dyadic system. We demonstrate the superiority of the proposed method via a detailed study on the dynamic model of the dyadic dynamic model.