In this paper, we propose World Model Policy Gradient (WMPG), an approach to reduce the variance of policy gradient estimates using learned world models (WM’s). In WMPG, a WM is trained online and used to imagine trajectories… The imagined trajectories are used in two ways. Firstly, to calculate a without-replacement estimator of the policy gradient. Secondly, the return of the imagined trajectories is used as an informed baseline. We compare the proposed approach with AC and MAC on a set […]

Generative adversarial networks (GANs) were originally envisioned as unsupervised generative models that learn to follow a target distribution. Variants such as conditional GANs, auxiliary-classifier GANs (ACGANs) project GANs on to supervised and semi-supervised learning frameworks by providing labelled data and using multi-class discriminators… In this paper, we approach the supervised GAN problem from a different perspective, one that is motivated by the philosophy of the famous Persian poet Rumi who said, “The art of knowing is knowing what to ignore.” […]

In this paper, we propose an evolutionary predatorprey robot system which can be generally implemented from simulation to the real world. We design the closed-loop robot system with camera and infrared sensors as inputs of controller… Both the predators and prey are co-evolved by NeuroEvolution of Augmenting Topologies (NEAT) to learn the expected behaviours. We design a framework that integrate Gym of OpenAI, Robot Operating System (ROS), Gazebo. In such a framework, users only need to focus on algorithms without […]

We describe algorithms that produce accurate real-time interactive in-space views of the eight Thurston geometries using ray-marching. We give a theoretical framework for our algorithms, independent of the geometry involved… In addition to scenes within a geometry $X$, we also consider scenes within quotient manifolds and orbifolds $X / Gamma$. We adapt the Phong lighting model to non-euclidean geometries. The most difficult part of this is the calculation of light intensity, which relates to the area density of geodesic spheres. […]

Despite tremendous success in many application scenarios, deep learning faces serious intellectual property (IP) infringement threats. Considering the cost of designing and training a good model, infringements will significantly infringe the interests of the original model owner… Recently, many impressive works have emerged for deep model IP protection. However, they either are vulnerable to ambiguity attacks, or require changes in the target network structure by replacing its original normalization layers and hence cause significant performance drops. To this end, we […]

One-shot weight sharing methods have recently drawn great attention in neural architecture search due to high efficiency and competitive performance. However, weight sharing across models has an inherent deficiency, i.e., insufficient training of subnetworks in the hypernetwork… To alleviate this problem, we present a simple yet effective architecture distillation method. The central idea is that subnetworks can learn collaboratively and teach each other throughout the training process, aiming to boost the convergence of individual models. We introduce the concept of […]

Diagnostic or procedural coding of clinical notes aims to derive a coded summary of disease-related information about patients. Such coding is usually done manually in hospitals but could potentially be automated to improve the efficiency and accuracy of medical coding… Recent studies on deep learning for automated medical coding achieved promising performances. However, the explainability of these models is usually poor, preventing them to be used confidently in supporting clinical practice. Another limitation is that these models mostly assume independence […]

The effectiveness of neural networks in solving complex problems is well recognized; however, little is known about their limitations. We demonstrate that the feed-forward architecture, for most commonly used activation functions, is incapable of approximating functions comprised of multiple sub-patterns while simultaneously respecting their composite-pattern structure… We overcome this bottleneck with a simple architecture modification that reallocates the neurons of any single feed-forward network across several smaller sub-networks, each specialized on a distinct part of the input-space. The modified architecture, […]

In this study, we detail the procedures for designing gain scheduling controllers by Linear Quadratic $H_infty$ robust optimization methods in Linear Matrix Inequalities (LMI) framework. The controllers are aimed at steering control of the autonomous vehicles… We first construct the Linear Parameter Varying (LPV) vehicle models and synthesize the robust controllers with uncertainty and nominal plants. We choose static output and state feedback controller structure to avoid higher order controllers considering implementation issues. The robust control problems are solved by […]