Simulation and Optimization of Mean First Passage Time Problems in 2-D using Numerical Embedded Methods and Perturbation Theory. (arXiv:1911.07842v1 [math.NA])

We develop novel numerical methods and perturbation approaches to determine the mean first passage time (MFPT) for a Brownian particle to be captured by either small stationary or mobile traps inside a bounded 2-D confining domain. Of particular interest is to identify optimal arrangements of small absorbing traps that minimize the average MFPT. Although the…

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…

Multiple Face Analyses through Adversarial Learning. (arXiv:1911.07846v1 [cs.CV])

This inherent relations among multiple face analysis tasks, such as landmark detection, head pose estimation, gender recognition and face attribute estimation are crucial to boost the performance of each task, but have not been thoroughly explored since typically these multiple face analysis tasks are handled as separate tasks. In this paper, we propose a novel…

Efficient Hardware Implementation of Incremental Learning and Inference on Chip. (arXiv:1911.07847v1 [cs.CV])

In this paper, we tackle the problem of incrementally learning a classifier, one example at a time, directly on chip. To this end, we propose an efficient hardware implementation of a recently introduced incremental learning procedure that achieves state-of-the-art performance by combining transfer learning with majority votes and quantization techniques. The proposed design is able…

Modality To Modality Translation: An Adversarial Representation Learning and Graph Fusion Network for Multimodal Fusion. (arXiv:1911.07848v1 [cs.CV])

Learning joint embedding space for various modalities is of vital importance for multimodal fusion. Mainstream modality fusion approaches fail to achieve this goal, leaving a modality gap which heavily affects cross-modal fusion. In this paper, we propose a novel adversarial encoder-decoder-classifier framework to learn a modality-invariant embedding space. Since the distributions of various modalities vary…

Temporal Knowledge Graph Embedding Model based on Additive Time Series Decomposition. (arXiv:1911.07893v1 [cs.LG])

Knowledge Graph (KG) embedding has attracted more attention in recent years. Most of KG embedding models learn from time-unaware triples. However, the inclusion of temporal information beside triples would further improve the performance of a KGE model. In this regard, we propose ATiSE, a temporal KG embedding model which incorporates time information into entity/relation representations…

Common Growth Patterns for Regional Social Networks: a Point Process Approach. (arXiv:1911.07902v1 [stat.AP])

Although recent research on social networks emphasizes microscopic dynamics such as retweets and social connectivity of an individual user, we focus on macroscopic growth dynamics of social network link formation. Rather than focusing on one particular dataset, we find invariant behavior in regional social networks that are geographically concentrated. Empirical findings suggest that the startup…

Comments on the Du-Kakade-Wang-Yang Lower Bounds. (arXiv:1911.07910v1 [cs.LG])

Du, Kakade, Wang, and Yang recently established intriguing lower bounds on sample complexity, which suggest that reinforcement learning with a misspecified representation is intractable. Another line of work, which centers around a statistic called the eluder dimension, establishes tractability of problems similar to those considered in the Du-Kakade-Wang-Yang paper. We compare these results and reconcile…