Search Results for author: Antonia Creswell

Found 21 papers, 7 papers with code

Language models show human-like content effects on reasoning

no code implementations14 Jul 2022 Ishita Dasgupta, Andrew K. Lampinen, Stephanie C. Y. Chan, Antonia Creswell, Dharshan Kumaran, James L. McClelland, Felix Hill

We find that state of the art large language models (with 7 or 70 billion parameters; Hoffman et al., 2022) reflect many of the same patterns observed in humans across these tasks -- like humans, models reason more effectively about believable situations than unrealistic or abstract ones.

Language Modelling Logical Reasoning +1

Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning

no code implementations19 May 2022 Antonia Creswell, Murray Shanahan, Irina Higgins

Large language models (LLMs) have been shown to be capable of impressive few-shot generalisation to new tasks.

Logical Reasoning

Can language models learn from explanations in context?

no code implementations5 Apr 2022 Andrew K. Lampinen, Ishita Dasgupta, Stephanie C. Y. Chan, Kory Matthewson, Michael Henry Tessler, Antonia Creswell, James L. McClelland, Jane X. Wang, Felix Hill

We evaluate the effects of various zero-shot and few-shot prompts that include different types of explanations, instructions, and controls on the performance of a range of large language models.

Scaling Language Models: Methods, Analysis & Insights from Training Gopher

no code implementations NA 2021 Jack W. Rae, Sebastian Borgeaud, Trevor Cai, Katie Millican, Jordan Hoffmann, Francis Song, John Aslanides, Sarah Henderson, Roman Ring, Susannah Young, Eliza Rutherford, Tom Hennigan, Jacob Menick, Albin Cassirer, Richard Powell, George van den Driessche, Lisa Anne Hendricks, Maribeth Rauh, Po-Sen Huang, Amelia Glaese, Johannes Welbl, Sumanth Dathathri, Saffron Huang, Jonathan Uesato, John Mellor, Irina Higgins, Antonia Creswell, Nat McAleese, Amy Wu, Erich Elsen, Siddhant Jayakumar, Elena Buchatskaya, David Budden, Esme Sutherland, Karen Simonyan, Michela Paganini, Laurent SIfre, Lena Martens, Xiang Lorraine Li, Adhiguna Kuncoro, Aida Nematzadeh, Elena Gribovskaya, Domenic Donato, Angeliki Lazaridou, Arthur Mensch, Jean-Baptiste Lespiau, Maria Tsimpoukelli, Nikolai Grigorev, Doug Fritz, Thibault Sottiaux, Mantas Pajarskas, Toby Pohlen, Zhitao Gong, Daniel Toyama, Cyprien de Masson d'Autume, Yujia Li, Tayfun Terzi, Vladimir Mikulik, Igor Babuschkin, Aidan Clark, Diego de Las Casas, Aurelia Guy, Chris Jones, James Bradbury, Matthew Johnson, Blake Hechtman, Laura Weidinger, Iason Gabriel, William Isaac, Ed Lockhart, Simon Osindero, Laura Rimell, Chris Dyer, Oriol Vinyals, Kareem Ayoub, Jeff Stanway, Lorrayne Bennett, Demis Hassabis, Koray Kavukcuoglu, Geoffrey Irving

Language modelling provides a step towards intelligent communication systems by harnessing large repositories of written human knowledge to better predict and understand the world.

Abstract Algebra Anachronisms +133

SIMONe: View-Invariant, Temporally-Abstracted Object Representations via Unsupervised Video Decomposition

no code implementations NeurIPS 2021 Rishabh Kabra, Daniel Zoran, Goker Erdogan, Loic Matthey, Antonia Creswell, Matthew Botvinick, Alexander Lerchner, Christopher P. Burgess

Leveraging the shared structure that exists across different scenes, our model learns to infer two sets of latent representations from RGB video input alone: a set of "object" latents, corresponding to the time-invariant, object-level contents of the scene, as well as a set of "frame" latents, corresponding to global time-varying elements such as viewpoint.

Instance Segmentation Semantic Segmentation

Unsupervised Object-Based Transition Models for 3D Partially Observable Environments

no code implementations NeurIPS 2021 Antonia Creswell, Rishabh Kabra, Chris Burgess, Murray Shanahan

We present a slot-wise, object-based transition model that decomposes a scene into objects, aligns them (with respect to a slot-wise object memory) to maintain a consistent order across time, and predicts how those objects evolve over successive frames.

AlignNet: Self-supervised Alignment Module

no code implementations25 Sep 2019 Antonia Creswell, Luis Piloto, David Barrett, Kyriacos Nikiforou, David Raposo, Marta Garnelo, Peter Battaglia, Murray Shanahan

The natural world consists of objects that we perceive as persistent in space and time, even though these objects appear, disappear and reappear in our field of view as we move.

Question Answering

An Explicitly Relational Neural Network Architecture

1 code implementation ICML 2020 Murray Shanahan, Kyriacos Nikiforou, Antonia Creswell, Christos Kaplanis, David Barrett, Marta Garnelo

With a view to bridging the gap between deep learning and symbolic AI, we present a novel end-to-end neural network architecture that learns to form propositional representations with an explicitly relational structure from raw pixel data.

Relational Reasoning

Inverting The Generator Of A Generative Adversarial Network (II)

1 code implementation15 Feb 2018 Antonia Creswell, Anil A. Bharath

Using our proposed inversion technique, we are able to identify which attributes of a dataset a trained GAN is able to model and quantify GAN performance, based on a reconstruction loss.

Denoising Adversarial Autoencoders: Classifying Skin Lesions Using Limited Labelled Training Data

no code implementations2 Jan 2018 Antonia Creswell, Alison Pouplin, Anil A. Bharath

We propose a novel deep learning model for classifying medical images in the setting where there is a large amount of unlabelled medical data available, but labelled data is in limited supply.

Denoising General Classification

LatentPoison -- Adversarial Attacks On The Latent Space

no code implementations ICLR 2018 Antonia Creswell, Biswa Sengupta, Anil A. Bharath

Robustness and security of machine learning (ML) systems are intertwined, wherein a non-robust ML system (classifiers, regressors, etc.)

General Classification reinforcement-learning

Adversarial Information Factorization

1 code implementation ICLR 2019 Antonia Creswell, Yumnah Mohamied, Biswa Sengupta, Anil A. Bharath

We propose a novel generative model architecture designed to learn representations for images that factor out a single attribute from the rest of the representation.

Facial Attribute Classification Image Generation

LatentPoison - Adversarial Attacks On The Latent Space

1 code implementation8 Nov 2017 Antonia Creswell, Anil A. Bharath, Biswa Sengupta

Robustness and security of machine learning (ML) systems are intertwined, wherein a non-robust ML system (classifiers, regressors, etc.)

General Classification reinforcement-learning

Generative Adversarial Networks: An Overview

2 code implementations19 Oct 2017 Antonia Creswell, Tom White, Vincent Dumoulin, Kai Arulkumaran, Biswa Sengupta, Anil A. Bharath

Generative adversarial networks (GANs) provide a way to learn deep representations without extensively annotated training data.

General Classification Image Generation +2

On denoising autoencoders trained to minimise binary cross-entropy

no code implementations28 Aug 2017 Antonia Creswell, Kai Arulkumaran, Anil A. Bharath

When training autoencoders on image data a natural choice of loss function is BCE, since pixel values may be normalised to take values in [0, 1] and the decoder model may be designed to generate samples that take values in (0, 1).


Denoising Adversarial Autoencoders

1 code implementation3 Mar 2017 Antonia Creswell, Anil Anthony Bharath

Autoencoders, a form of generative model, may be trained by learning to reconstruct unlabelled input data from a latent representation space.

Denoising General Classification

Inverting The Generator Of A Generative Adversarial Network

no code implementations17 Nov 2016 Antonia Creswell, Anil Anthony Bharath

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.

Image Classification Image Retrieval +1

Improving Sampling from Generative Autoencoders with Markov Chains

1 code implementation28 Oct 2016 Antonia Creswell, Kai Arulkumaran, Anil Anthony Bharath

Generative autoencoders are those which are trained to softly enforce a prior on the latent distribution learned by the inference model.

Task Specific Adversarial Cost Function

no code implementations27 Sep 2016 Antonia Creswell, Anil A. Bharath

The cost function used to train a generative model should fit the purpose of the model.

One-Shot Learning

Adversarial Training For Sketch Retrieval

no code implementations10 Jul 2016 Antonia Creswell, Anil Anthony Bharath

Generative Adversarial Networks (GAN) are able to learn excellent representations for unlabelled data which can be applied to image generation and scene classification.

Image Generation Scene Classification +1

Cannot find the paper you are looking for? You can Submit a new open access paper.