Search Results - "Higgins, Irina"

Unsupervised deep learning identifies semantic disentanglement in single inferotemporal face patch neurons by Higgins, Irina, Chang, Le, Langston, Victoria, Hassabis, Demis, Summerfield, Christopher, Tsao, Doris, Botvinick, Matthew

“…In order to better understand how the brain perceives faces, it is important to know what objective drives learning in the ventral visual stream. To answer…”
Get full text

Symmetry-Based Representations for Artificial and Biological General Intelligence by Higgins, Irina, Racanière, Sébastien, Rezende, Danilo

“…Biological intelligence is remarkable in its ability to produce complex behavior in many diverse situations through data efficient, generalizable, and…”
Get full text

Unsupervised learning of temporal features for word categorization in a spiking neural network model of the auditory brain by Higgins, Irina, Stringer, Simon, Schnupp, Jan

“…The nature of the code used in the auditory cortex to represent complex auditory stimuli, such as naturally spoken words, remains a matter of debate. Here we…”
Get full text

Generalizing universal function approximators by Higgins, Irina

“…At the heart of many challenges in scientific research lie complex equations for which no analytical solutions exist. A new neural network model called…”
Get full text

Harmonic Training and the Formation of Pitch Representation in a Neural Network Model of the Auditory Brain by Ahmad, Nasir, Higgins, Irina, Walker, Kerry M M, Stringer, Simon M

“…Attempting to explain the perceptual qualities of pitch has proven to be, and remains, a difficult problem. The wide range of sounds which elicit pitch and a…”
Get full text

Computational neuroscience of speech recognition by Higgins, Irina

“…Physical variability of speech combined with its perceptual constancy make speech recognition a challenging task. The human auditory brain, however, is able to…”
Get full text

Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning by Creswell, Antonia, Shanahan, Murray, Higgins, Irina

“…Large language models (LLMs) have been shown to be capable of impressive few-shot generalisation to new tasks. However, they still tend to perform poorly on…”
Get full text

Symmetry-Based Representations for Artificial and Biological General Intelligence by Higgins, Irina, Racanière, Sébastien, Rezende, Danilo

“…Biological intelligence is remarkable in its ability to produce complex behaviour in many diverse situations through data efficient, generalisable and…”
Get full text

Learning view invariant recognition with partially occluded objects by Tromans, James M, Higgins, Irina, Stringer, Simon M

“…This paper investigates how a neural network model of the ventral visual pathway, VisNet, can form separate view invariant representations of a number of…”
Get full text

SyMetric: Measuring the Quality of Learnt Hamiltonian Dynamics Inferred from Vision by Higgins, Irina, Wirnsberger, Peter, Jaegle, Andrew, Botev, Aleksandar

“…A recently proposed class of models attempts to learn latent dynamics from high-dimensional observations, like images, using priors informed by Hamiltonian…”
Get full text

Which priors matter? Benchmarking models for learning latent dynamics by Botev, Aleksandar, Jaegle, Andrew, Wirnsberger, Peter, Hennes, Daniel, Higgins, Irina

“…Learning dynamics is at the heart of many important applications of machine learning (ML), such as robotics and autonomous driving. In these settings, ML…”
Get full text

Disentangling by Subspace Diffusion by Pfau, David, Higgins, Irina, Botev, Aleksandar, Racanière, Sébastien

“…We present a novel nonparametric algorithm for symmetry-based disentangling of data manifolds, the Geometric Manifold Component Estimator (GEOMANCER)…”
Get full text

Solving math word problems with process- and outcome-based feedback by Uesato, Jonathan, Kushman, Nate, Kumar, Ramana, Song, Francis, Siegel, Noah, Wang, Lisa, Creswell, Antonia, Irving, Geoffrey, Higgins, Irina

“…Recent work has shown that asking language models to generate reasoning steps improves performance on many reasoning tasks. When moving beyond prompting, this…”
Get full text

Representation Matters: Improving Perception and Exploration for Robotics by Wulfmeier, Markus, Byravan, Arunkumar, Hertweck, Tim, Higgins, Irina, Gupta, Ankush, Kulkarni, Tejas, Reynolds, Malcolm, Teplyashin, Denis, Hafner, Roland, Lampe, Thomas, Riedmiller, Martin

“…Projecting high-dimensional environment observations into lower-dimensional structured representations can considerably improve data-efficiency for…”
Get full text

Equivariant Hamiltonian Flows by Rezende, Danilo Jimenez, Racanière, Sébastien, Higgins, Irina, Toth, Peter

“…This paper introduces equivariant hamiltonian flows, a method for learning expressive densities that are invariant with respect to a known Lie-algebra of local…”
Get full text

Unsupervised deep learning identifies semantic disentanglement in single inferotemporal neurons by Higgins, Irina, Chang, Le, Langston, Victoria, Hassabis, Demis, Summerfield, Christopher, Tsao, Doris, Botvinick, Matthew

“…Deep supervised neural networks trained to classify objects have emerged as popular models of computation in the primate ventral stream. These models represent…”
Get full text

Representation learning for improved interpretability and classification accuracy of clinical factors from EEG by Honke, Garrett, Higgins, Irina, Thigpen, Nina, Miskovic, Vladimir, Link, Katie, Duan, Sunny, Gupta, Pramod, Klawohn, Julia, Hajcak, Greg

“…Despite extensive standardization, diagnostic interviews for mental health disorders encompass substantial subjective judgment. Previous studies have…”
Get full text

Disentangled Cumulants Help Successor Representations Transfer to New Tasks by Grimm, Christopher, Higgins, Irina, Barreto, Andre, Teplyashin, Denis, Wulfmeier, Markus, Hertweck, Tim, Hadsell, Raia, Singh, Satinder

“…Biological intelligence can learn to solve many diverse tasks in a data efficient manner by re-using basic knowledge and skills from one task to another…”
Get full text

Hamiltonian Generative Networks by Toth, Peter, Rezende, Danilo Jimenez, Jaegle, Andrew, Racanière, Sébastien, Botev, Aleksandar, Higgins, Irina

“…The Hamiltonian formalism plays a central role in classical and quantum physics. Hamiltonians are the main tool for modelling the continuous time evolution of…”
Get full text

Unsupervised Model Selection for Variational Disentangled Representation Learning by Duan, Sunny, Matthey, Loic, Saraiva, Andre, Watters, Nicholas, Burgess, Christopher P, Lerchner, Alexander, Higgins, Irina

“…Disentangled representations have recently been shown to improve fairness, data efficiency and generalisation in simple supervised and reinforcement learning…”
Get full text