Search Results for author:
Found 29 papers, 9 papers with code
Synthnet: Learning synthesizers end-to-end
Learning synthesizers and generating music in the raw audio domain is a challenging task.
BAIT: Benchmarking (Embedding) Architectures for Interactive Theorem-Proving
We also provide a qualitative analysis, illustrating that improved performance is associated with more semantically-aware embeddings.
Latent Optimal Paths by Gumbel Propagation for Variational Bayesian Dynamic Programming
We propose a unified approach to obtain structured sparse optimal paths in the latent space of a variational autoencoder (VAE) using dynamic programming and Gumbel propagation.
DualVAE: Controlling Colours of Generated and Real Images
The disentangled representation is obtained by two novel mechanisms: (i) a dual branch architecture that separates image colour attributes from geometric attributes, and (ii) a new ELBO that trains the combined colour and geometry representations.
R-U-SURE? Uncertainty-Aware Code Suggestions By Maximizing Utility Across Random User Intents
Large language models show impressive results at predicting structured text such as code, but also commonly introduce errors and hallucinations in their output.
Sampled Transformer for Point Sets
The sparse transformer can reduce the computational complexity of the self-attention layers to $O(n)$, whilst still being a universal approximator of continuous sequence-to-sequence functions.
LegendreTron: Uprising Proper Multiclass Loss Learning
Existing methods do this by fitting an inverse canonical link function which monotonically maps $\mathbb{R}$ to $[0, 1]$ to estimate probabilities for binary problems.
Determinantal Point Process Likelihoods for Sequential Recommendation
Sequential recommendation is a popular task in academic research and close to real-world application scenarios, where the goal is to predict the next action(s) of the user based on his/her previous sequence of actions.
SPA-VAE: Similar-Parts-Assignment for Unsupervised 3D Point Cloud Generation
This paper addresses the problem of unsupervised parts-aware point cloud generation with learned parts-based self-similarity.
Dense Uncertainty Estimation
Deep neural networks can be roughly divided into deterministic neural networks and stochastic neural networks. The former is usually trained to achieve a mapping from input space to output space via maximum likelihood estimation for the weights, which leads to deterministic predictions during testing.
EditVAE: Unsupervised Part-Aware Controllable 3D Point Cloud Shape Generation
We achieve this with a simple modification of the Variational Auto-Encoder which yields a joint model of the point cloud itself along with a schematic representation of it as a combination of shape primitives.
Designing Less Forgetful Networks for Continual Learning
Neural networks usually excel in learning a single task.
Humanly Certifying Superhuman Classifiers
In this paper, we first raise the challenge of evaluating the performance of both humans and models with respect to an oracle which is unobserved.
Learning to Continually Learn Rapidly from Few and Noisy Data
Neural networks suffer from catastrophic forgetting and are unable to sequentially learn new tasks without guaranteed stationarity in data distribution.
TacticZero: Learning to Prove Theorems from Scratch with Deep Reinforcement Learning
We propose a novel approach to interactive theorem-proving (ITP) using deep reinforcement learning.
Highway-Connection Classifier Networks for Plastic yet Stable Continual Learning
Catastrophic forgetting occurs when a neural network is trained sequentially on multiple tasks – its weights will be continuously modified and as a result, the network will lose its ability in solving a previous task.
MTL2L: A Context Aware Neural Optimiser
Learning to learn (L2L) trains a meta-learner to assist the learning of a task-specific base learner.
All your loss are belong to Bayes
Loss functions are a cornerstone of machine learning and the starting point of most algorithms.
EINS: Long Short-Term Memory with Extrapolated Input Network Simplification
This paper contrasts the two canonical recurrent neural networks (RNNs) of long short-term memory (LSTM) and gated recurrent unit (GRU) to propose our novel light-weight RNN of Extrapolated Input for Network Simplification (EINS).
Computer Assisted Composition in Continuous Time
We address the problem of combining sequence models of symbolic music with user defined constraints.
Variational Inference for Sparse Gaussian Process Modulated Hawkes Process
We validate the efficiency of our accelerated variational inference schema and practical utility of our tighter ELBO for model selection.
Efficient Non-parametric Bayesian Hawkes Processes
On two large-scale Twitter diffusion datasets, we show that our methods outperform the current state-of-the-art in goodness-of-fit and that the time complexity is linear in the size of the dataset.
DecayNet: A Study on the Cell States of Long Short Term Memories
It is unclear whether the extensively applied long-short term memory (LSTM) is an optimised architecture for recurrent neural networks.
Monge blunts Bayes: Hardness Results for Adversarial Training
A key feature of our result is that it holds for all proper losses, and for a popular subset of these, the optimisation of this central measure appears to be independent of the loss.
Self-Bounded Prediction Suffix Tree via Approximate String Matching
Prediction suffix trees (PST) provide an effective tool for sequence modelling and prediction.
Computer Assisted Composition with Recurrent Neural Networks
For the case of highly permissive constraint sets, we find that sampling is to be preferred due to the overly regular nature of the optimisation based results.
Symbolic Music Data Version 1.0
We also define training, testing and validation splits for the new dataset, based on a clustering scheme which we also describe.
Modelling Symbolic Music: Beyond the Piano Roll
In this paper, we consider the problem of probabilistically modelling symbolic music data.
Sound
Diffeomorphic Dimensionality Reduction
This paper introduces a new approach to constructing meaningful lower dimensional representations of sets of data points.
