Search Results for author:
Found 15 papers, 8 papers with code
High-resolution 3D Maps of Left Atrial Displacements using an Unsupervised Image Registration Neural Network
Functional analysis of the left atrium (LA) plays an increasingly important role in the prognosis and diagnosis of cardiovascular diseases.
Disentangled Generative Models for Robust Prediction of System Dynamics
Deep neural networks have become increasingly of interest in dynamical system prediction, but out-of-distribution generalization and long-term stability still remains challenging.
Diversity-based Trajectory and Goal Selection with Hindsight Experience Replay
We evaluate DTGSH on five challenging robotic manipulation tasks in simulated robot environments, where we show that our method can learn more quickly and reach higher performance than other state-of-the-art approaches on all tasks.
Fully Convolutional Approach for Simulating Wave Dynamics
In this work, we investigate the performance of fully convolutional networks to predict the motion and interaction of surface waves in open and closed complex geometries.
Episodic Self-Imitation Learning with Hindsight
The trajectory selection module is shown to prevent the agent learning undesirable hindsight experiences.
Analysing Deep Reinforcement Learning Agents Trained with Domain Randomisation
Furthermore, even with an improved saliency method introduced in this work, we show that qualitative studies may not always correspond with quantitative measures, necessitating the combination of inspection tools in order to provide sufficient insights into the behaviour of trained agents.
Memory-Efficient Episodic Control Reinforcement Learning with Dynamic Online k-means
Recently, neuro-inspired episodic control (EC) methods have been developed to overcome the data-inefficiency of standard deep reinforcement learning approaches.
Sample-Efficient Reinforcement Learning with Maximum Entropy Mellowmax Episodic Control
Deep networks have enabled reinforcement learning to scale to more complex and challenging domains, but these methods typically require large quantities of training data.
A Recursive Bayesian Approach To Describe Retinal Vasculature Geometry
In this study, we introduce three information sources for width estimation.
A Brief Survey of Deep Reinforcement Learning
Deep reinforcement learning is poised to revolutionise the field of AI and represents a step towards building autonomous systems with a higher level understanding of the visual world.
Denoising Adversarial Autoencoders
Autoencoders, a form of generative model, may be trained by learning to reconstruct unlabelled input data from a latent representation space.
Inverting The Generator Of A Generative Adversarial Network
When the high-dimensional distribution describes images of a particular data set, the network should learn to generate visually similar image samples for latent variables that are close to each other in the latent space.
Improving Sampling from Generative Autoencoders with Markov Chains
Generative autoencoders are those which are trained to softly enforce a prior on the latent distribution learned by the inference model.
Adversarial Training For Sketch Retrieval
Generative Adversarial Networks (GAN) are able to learn excellent representations for unlabelled data which can be applied to image generation and scene classification.
Classifying Options for Deep Reinforcement Learning
In this paper we combine one method for hierarchical reinforcement learning - the options framework - with deep Q-networks (DQNs) through the use of different "option heads" on the policy network, and a supervisory network for choosing between the different options.
Hierarchical Reinforcement Learning
reinforcement-learning
+1
