Safety Augmented Value Estimation from Demonstrations (SAVED): Safe Deep Model-Based RL for Sparse Cost Robotic Tasks. (arXiv:1905.13402v4 [cs.LG] UPDATED)

Reinforcement learning (RL) for robotics is challenging due to the difficulty in hand-engineering a dense cost function, which can lead to unintended behavior, and dynamical uncertainty, which makes it hard to enforce constraints during learning. We address these issues with a new model-based reinforcement learning algorithm, safety augmented value estimation from demonstrations (SAVED), which uses…

Leveraging Simple Model Predictions for Enhancing its Performance. (arXiv:1905.13565v2 [cs.LG] UPDATED)

There has been recent interest in improving performance of simple models for multiple reasons such as interpretability, robust learning from small data, deployment in memory constrained settings as well as environmental considerations. In this paper, we propose a novel method SRatio that can utilize information from high performing complex models (viz. deep neural networks, boosted…

Exploiting Human Social Cognition for the Detection of Fake and Fraudulent Faces via Memory Networks. (arXiv:1911.07844v1 [cs.CV])

Advances in computer vision have brought us to the point where we have the ability to synthesise realistic fake content. Such approaches are seen as a source of disinformation and mistrust, and pose serious concerns to governments around the world. Convolutional Neural Networks (CNNs) demonstrate encouraging results when detecting fake images that arise from the…

Neural Forest Learning. (arXiv:1911.07845v1 [cs.LG])

We propose Neural Forest Learning (NFL), a novel deep learning based random-forest-like method. In contrast to previous forest methods, NFL enjoys the benefits of end-to-end, data-driven representation learning, as well as pervasive support from deep learning software and hardware platforms, hence achieving faster inference speed and higher accuracy than previous forest methods. Furthermore, NFL learns…

Co-Attentive Equivariant Neural Networks: Focusing Equivariance On Transformations Co-Occurring In Data. (arXiv:1911.07849v1 [cs.CV])

Equivariance is a nice property to have as it produces much more parameter efficient neural architectures and preserves the structure of the input through the feature mapping. Even though some combinations of transformations might never appear (e.g. an upright face with a horizontal nose), current equivariant architectures consider the set of all possible transformations in…

RWNE: A Scalable Random-Walk based Network Embedding Framework with Personalized Higher-order Proximity Preserved. (arXiv:1911.07874v1 [cs.LG])

Higher-order proximity preserved network embedding has attracted increasing attention recently. In particular, due to the superior scalability, random-walk based network embedding has also been well developed, which could efficiently explore higher-order neighborhood via multi-hop random walks. However, despite the success of current random-walk based methods, most of them are usually not expressive enough to preserve…

Cooperative Pathfinding based on high-scalability Multi-agent RRT*. (arXiv:1911.07840v1 [cs.MA])

Problems that claim several agents to find no-conflicts paths from their start locations to their destinations are named as cooperative pathfinding problems. This problem can be efficiently solved by the Multi-agent RRT*(MA-RRT*) algorithm, which offers better scalability than some traditional algorithms, such as Optimal Anytime(OA), in sparse environments. However, MA-RRT* cannot effectively find solutions in…

Tigris: Architecture and Algorithms for 3D Perception in Point Clouds. (arXiv:1911.07841v1 [cs.CV])

Machine perception applications are increasingly moving toward manipulating and processing 3D point cloud. This paper focuses on point cloud registration, a key primitive of 3D data processing widely used in high-level tasks such as odometry, simultaneous localization and mapping, and 3D reconstruction. As these applications are routinely deployed in energy-constrained environments, real-time and energy-efficient point…