Search Results for author:
Found 19 papers, 7 papers with code
Bridging the Human-AI Knowledge Gap: Concept Discovery and Transfer in AlphaZero
Artificial Intelligence (AI) systems have made remarkable progress, attaining super-human performance across various domains.
Role of Human-AI Interaction in Selective Prediction
Using real-world conservation data and a selective prediction system that improves expected accuracy over that of the human or AI system working individually, we show that this messaging has a significant impact on the accuracy of human judgements.
Acquisition of Chess Knowledge in AlphaZero
In this work we provide evidence that human knowledge is acquired by the AlphaZero neural network as it trains on the game of chess.
Assessing Game Balance with AlphaZero: Exploring Alternative Rule Sets in Chess
We compare nine other variants that involve atomic changes to the rules of chess.
Unsupervised Separation of Dynamics from Pixels
We present an approach to learn the dynamics of multiple objects from image sequences in an unsupervised way.
A Factorial Mixture Prior for Compositional Deep Generative Models
We assume that a high-dimensional datum, like an image, is a compositional expression of a set of properties, with a complicated non-linear relationship between the datum and its properties.
An Efficient Implementation of Riemannian Manifold Hamiltonian Monte Carlo for Gaussian Process Models
This technical report presents pseudo-code for a Riemannian manifold Hamiltonian Monte Carlo (RMHMC) method to efficiently simulate samples from $N$-dimensional posterior distributions $p(x|y)$, where $x \in R^N$ is drawn from a Gaussian Process (GP) prior, and observations $y_n$ are independent given $x_n$.
Recurrent Relational Networks for complex relational reasoning
Humans possess an ability to abstractly reason about objects and their interactions, an ability not shared with state-of-the-art deep learning models.
Recurrent Relational Networks
We achieve state of the art results on the bAbI textual question-answering dataset with the recurrent relational network, consistently solving 20/20 tasks.
Ranked #3 on
Question Answering
on bAbi
(Mean Error Rate metric)
A Disentangled Recognition and Nonlinear Dynamics Model for Unsupervised Learning
This paper takes a step towards temporal reasoning in a dynamically changing video, not in the pixel space that constitutes its frames, but in a latent space that describes the non-linear dynamics of the objects in its world.
The Bayesian Low-Rank Determinantal Point Process Mixture Model
Determinantal point processes (DPPs) are an elegant model for encoding probabilities over subsets, such as shopping baskets, of a ground set, such as an item catalog.
Sequential Neural Models with Stochastic Layers
How can we efficiently propagate uncertainty in a latent state representation with recurrent neural networks?
An Adaptive Resample-Move Algorithm for Estimating Normalizing Constants
The estimation of normalizing constants is a fundamental step in probabilistic model comparison.
Low-Rank Factorization of Determinantal Point Processes for Recommendation
In this work we present a new method for learning the DPP kernel from observed data using a low-rank factorization of this kernel.
On the Convergence of Stochastic Variational Inference in Bayesian Networks
We highlight a pitfall when applying stochastic variational inference to general Bayesian networks.
Scalable Bayesian Modelling of Paired Symbols
We present a novel, scalable and Bayesian approach to modelling the occurrence of pairs of symbols (i, j) drawn from a large vocabulary.
One-class Collaborative Filtering with Random Graphs: Annotated Version
The bane of one-class collaborative filtering is interpreting and modelling the latent signal from the missing class.
Perturbative Corrections for Approximate Inference in Gaussian Latent Variable Models
A perturbative expansion is made of the exact but intractable correction, and can be applied to the model's partition function and other moments of interest.
Improving on Expectation Propagation
We develop as series of corrections to Expectation Propagation (EP), which is one of the most popular methods for approximate probabilistic inference.
