Learning how to model networks – We present a novel technique for learning deep machine-learning representations of images by learning a deep model of the network structure, and then applying it to the task of image classification. We show that our deep model is able to achieve better classification performance for images compared to prior state-of-the-art methods. While previous approaches focus on learning from the network structure, our model can handle images from a much larger network structure using only a single learned feature learned from the network images. We show in the literature that our approach can improve classification performance.
The goal of this paper is to provide an efficient and robust implementation of a new distributed inference methodology that is able to capture and model the dependencies among agents. We describe the algorithm and the implementation for a new policy architecture, which supports many agents, including many robots. We also discuss the possibility of a future vision for our methodology, which is based on learning to reason.
Deep Learning for Real-Time Financial Transaction Graphs with Confounding Effects of Connectomics
Recurrent Neural Networks for Activity Recognition in Video Sequences
Learning how to model networks
A Semi-automated Test and Evaluation System for Multi-Person Pose Estimation
Convergent Inference Policies for Reinforcement LearningThe goal of this paper is to provide an efficient and robust implementation of a new distributed inference methodology that is able to capture and model the dependencies among agents. We describe the algorithm and the implementation for a new policy architecture, which supports many agents, including many robots. We also discuss the possibility of a future vision for our methodology, which is based on learning to reason.