
TorchIO: a Python library for efficient loading, preprocessing, augmentation and patchbased sampling of medical images in deep learning
We present TorchIO, an opensource Python library for efficient loading,...
read it

Degenerative Adversarial NeuroImage Nets for 3D Simulations: Application in Longitudinal MRI
The recent success of deep learning together with the availability of la...
read it

A Survey on Contextual Embeddings
Contextual embeddings, such as ELMo and BERT, move beyond global word re...
read it

Unsupervised KnowledgeTransfer for Learned Image Reconstruction
Deep learningbased image reconstruction approaches have demonstrated im...
read it

OffPolicy Reinforcement Learning for Efficient and Effective GAN Architecture Search
In this paper, we introduce a new reinforcement learning (RL) based neur...
read it

Lautum Regularization for Semisupervised Transfer Learning
Transfer learning is a very important tool in deep learning as it allows...
read it

Margin Maximization as Lossless Maximal Compression
The ultimate goal of a supervised learning algorithm is to produce model...
read it

Disentangling Interpretable Generative Parameters of Random and RealWorld Graphs
While a wide range of interpretable generative procedures for graphs exi...
read it

PiNet: A Permutation Invariant Graph Neural Network for Graph Classification
We propose an endtoend deep learning learning model for graph classifi...
read it

The relationship between dynamic programming and active inference: the discrete, finitehorizon case
Active inference is a normative framework for generating behaviour based...
read it

On Margins and Derandomisation in PACBayes
We develop a framework for derandomising PACBayesian generalisation bou...
read it

Neural Empirical Bayes
We formulate a novel framework that unifies kernel density estimation an...
read it

Improving the Robustness of Graphs through Reinforcement Learning and Graph Neural Networks
Graphs can be used to represent and reason about real world systems. A v...
read it

PACBayes Analysis Beyond the Usual Bounds
We focus on a stochastic learning model where the learner observes a fin...
read it

Deep active inference agents using MonteCarlo methods
Active inference is a Bayesian framework for understanding biological in...
read it

InformationTheoretic Bounds on the Moments of the Generalization Error of Learning Algorithms
Generalization error bounds are critical to understanding the performanc...
read it

Kernel Instrumental Variable Regression
Instrumental variable regression is a strategy for learning causal relat...
read it

SentiMATE: Learning to play Chess through Natural Language Processing
We present SentiMATE, a novel endtoend Deep Learning model for Chess, ...
read it

Predicting Engagement in Video Lectures
The explosion of Open Educational Resources (OERs) in the recent years c...
read it

Learning a Neural 3D Texture Space from 2D Exemplars
We propose a generative model of 2D and 3D natural textures with diversi...
read it

MultiTask Recurrent Neural Network for Surgical Gesture Recognition and Progress Prediction
Surgical gesture recognition is important for surgical data science and ...
read it

An Algorithm for Learning Shape and Appearance Models without Annotations
This paper presents a framework for automatically learning shape and app...
read it

Probabilistic Recursive Reasoning for MultiAgent Reinforcement Learning
Humans are capable of attributing latent mental contents such as beliefs...
read it

Stochastic Filter Groups for MultiTask CNNs: Learning Specialist and Generalist Convolution Kernels
The performance of multitask learning in Convolutional Neural Networks ...
read it

Synthetic and Real Inputs for Tool Segmentation in Robotic Surgery
Semantic tool segmentation in surgical videos is important for surgical ...
read it

A Foliated View of Transfer Learning
Transfer learning considers a learning process where a new task is solve...
read it

Upper and Lower Bounds on the Performance of Kernel PCA
Principal Component Analysis (PCA) is a popular method for dimension red...
read it

Neighborhood Cognition Consistent MultiAgent Reinforcement Learning
Social psychology and real experiences show that cognitive consistency p...
read it

Better Boosting with Bandits for Online Learning
Probability estimates generated by boosting ensembles are poorly calibra...
read it

Neuromorphologicalypreserving Volumetric data encoding using VQVAE
The increasing efficiency and compactness of deep learning architectures...
read it

Differentiable PACBayes Objectives with Partially Aggregated Neural Networks
We make three related contributions motivated by the challenge of traini...
read it

ComBiNet: Compact Convolutional Bayesian Neural Network for Image Segmentation
Fully convolutional Ushaped neural networks have largely been the domin...
read it

On the Importance of Strong Baselines in Bayesian Deep Learning
Like all subfields of machine learning, Bayesian Deep Learning is drive...
read it

Optimizing Objectbased Perception and Control by FreeEnergy Principle
One of the wellknown formulations of human perception is a hierarchical...
read it

Methods and opensource toolkit for analyzing and visualizing challenge results
Biomedical challenges have become the de facto standard for benchmarking...
read it

TrueLearn: A Family of Bayesian Algorithms to Match Lifelong Learners to Open Educational Resources
The recent advances in computerassisted learning systems and the availa...
read it

Tighter risk certificates for neural networks
This paper presents empirical studies regarding training probabilistic n...
read it

Generative Modelling of BRDF Textures from Flash Images
We learn a latent space for easy capture, semantic editing, consistent i...
read it

Optimizing CNNbased Hyperspectral ImageClassification on FPGAs
Hyperspectral image (HSI) classification has been widely adopted in appl...
read it

Spatiotemporal GraphRNN for Point Cloud Prediction
In this paper, we propose an endtoend learning network to predict futu...
read it

Monte Carlo Convolution for Learning on NonUniformly Sampled Point Clouds
We propose an efficient and effective method to learn convolutions for n...
read it

Learning Shared Dynamics with MetaWorld Models
Humans have consciousness as the ability to perceive events and objects:...
read it

Modelling urban networks using Variational Autoencoders
A longstanding question for urban and regional planners pertains to the...
read it

Dynamic Face Video Segmentation via Reinforcement Learning
For realtime semantic video segmentation, most recent works utilise a d...
read it

SynthCity: A large scale synthetic point cloud
With deep learning becoming a more prominent approach for automatic clas...
read it

Empirical Bayesian Mixture Models for Medical Image Translation
Automatically generating one medical imaging modality from another is kn...
read it

A Learning Strategy for Contrastagnostic MRI Segmentation
We present a deep learning strategy that enables, for the first time, co...
read it

There is Strength in Numbers: Avoiding the HypothesisOnly Bias in Natural Language Inference via Ensemble Adversarial Training
Natural Language Inference (NLI) datasets contain annotation artefacts r...
read it

An AutoEncoder Strategy for Adaptive Image Segmentation
Deep neural networks are powerful tools for biomedical image segmentatio...
read it

MultipleIdentity Image Attacks Against Facebased Identity Verification
Facial verification systems are vulnerable to poisoning attacks that mak...
read it
UCL
University College London is a public research university in London, England, and a constituent college of the federal University of London.