Collaborating Authors

Discriminability-Based Transfer between Neural Networks

Neural Information Processing Systems

Neural networks are usually trained from scratch, relying only on the training data for guidance. However, as more and more networks are trained for various tasks, it becomes reasonable to seek out methods that.

A Cover-Based Approach to Multi-Agent Moving Target Pursuit

AAAI Conferences

We explore the task of designing an efficient multi-agent system that is capable of capturing a single moving target, assuming that every agent knows the location of all agents on a fixed known graph. Many existing approaches are suboptimal as they do not coordinate multiple pursuers and are slow as they re-plan each time the target moves, which makes them fare poorly in real-time pursuit scenarios such as video games. We address these shortcomings by developing the concept of cover set, which leads to a measure that takes advantage of information about the position and speed of each agent. We first define cover set and then present an algorithm that uses cover to coordinate multiple pursuers. We compare the effectiveness of this algorithm against several classic and state-of-the-art pursuit algorithms, along several performance measures. We also compute the optimal pursuit policy for several small grids, and use the associated optimal scores as yardsticks for our analysis.

A Transfer Learning Approach for Learning Temporal Nodes Bayesian Networks

AAAI Conferences

Situations where there is insufficient information to learn from often arise, and the process to recollect data can be expensive or in some cases take too long resulting in outdated models. Transfer learning strategies have proven to be a powerful technique to learn models from several sources when a single source does not provide enough information. In this work we present a methodology to learn a Temporal Nodes Bayesian Network by transferring knowledge from several different but related domains. Experiments based on a reference network show promising results, supporting our claim that transfer learning is a viable strategy to learn these models when scarce data is available.

Online Multi-Target Tracking Using Recurrent Neural Networks

AAAI Conferences

We present a novel approach to online multi-target tracking based on recurrent neural networks (RNNs). Tracking multiple objects in real-world scenes involves many challenges, including a) an a-priori unknown and time-varying number of targets, b) a continuous state estimation of all present targets, and c) a discrete combinatorial problem of data association. Most previous methods involve complex models that require tedious tuning of parameters. Here, we propose for the first time, an end-to-end learning approach for online multi-target tracking. Existing deep learning methods are not designed for the above challenges and cannot be trivially applied to the task. Our solution addresses all of the above points in a principled way. Experiments on both synthetic and real data show promising results obtained at ~300 Hz on a standard CPU, and pave the way towards future research in this direction.