Models, code, and papers for "Andrew Brock":

Large Scale GAN Training for High Fidelity Natural Image Synthesis

Sep 28, 2018
Andrew Brock, Jeff Donahue, Karen Simonyan

Despite recent progress in generative image modeling, successfully generating high-resolution, diverse samples from complex datasets such as ImageNet remains an elusive goal. To this end, we train Generative Adversarial Networks at the largest scale yet attempted, and study the instabilities specific to such scale. We find that applying orthogonal regularization to the generator renders it amenable to a simple "truncation trick", allowing fine control over the trade-off between sample fidelity and variety by truncating the latent space. Our modifications lead to models which set the new state of the art in class-conditional image synthesis. When trained on ImageNet at 128x128 resolution, our models (BigGANs) achieve an Inception Score (IS) of 166.3 and Frechet Inception Distance (FID) of 9.6, improving over the previous best IS of 52.52 and FID of 18.65.


  Click for Model/Code and Paper
SMASH: One-Shot Model Architecture Search through HyperNetworks

Aug 17, 2017
Andrew Brock, Theodore Lim, J. M. Ritchie, Nick Weston

Designing architectures for deep neural networks requires expert knowledge and substantial computation time. We propose a technique to accelerate architecture selection by learning an auxiliary HyperNet that generates the weights of a main model conditioned on that model's architecture. By comparing the relative validation performance of networks with HyperNet-generated weights, we can effectively search over a wide range of architectures at the cost of a single training run. To facilitate this search, we develop a flexible mechanism based on memory read-writes that allows us to define a wide range of network connectivity patterns, with ResNet, DenseNet, and FractalNet blocks as special cases. We validate our method (SMASH) on CIFAR-10 and CIFAR-100, STL-10, ModelNet10, and Imagenet32x32, achieving competitive performance with similarly-sized hand-designed networks. Our code is available at https://github.com/ajbrock/SMASH


  Click for Model/Code and Paper
FreezeOut: Accelerate Training by Progressively Freezing Layers

Jun 18, 2017
Andrew Brock, Theodore Lim, J. M. Ritchie, Nick Weston

The early layers of a deep neural net have the fewest parameters, but take up the most computation. In this extended abstract, we propose to only train the hidden layers for a set portion of the training run, freezing them out one-by-one and excluding them from the backward pass. Through experiments on CIFAR, we empirically demonstrate that FreezeOut yields savings of up to 20% wall-clock time during training with 3% loss in accuracy for DenseNets, a 20% speedup without loss of accuracy for ResNets, and no improvement for VGG networks. Our code is publicly available at https://github.com/ajbrock/FreezeOut

* Extended Abstract 

  Click for Model/Code and Paper
Neural Photo Editing with Introspective Adversarial Networks

Feb 06, 2017
Andrew Brock, Theodore Lim, J. M. Ritchie, Nick Weston

The increasingly photorealistic sample quality of generative image models suggests their feasibility in applications beyond image generation. We present the Neural Photo Editor, an interface that leverages the power of generative neural networks to make large, semantically coherent changes to existing images. To tackle the challenge of achieving accurate reconstructions without loss of feature quality, we introduce the Introspective Adversarial Network, a novel hybridization of the VAE and GAN. Our model efficiently captures long-range dependencies through use of a computational block based on weight-shared dilated convolutions, and improves generalization performance with Orthogonal Regularization, a novel weight regularization method. We validate our contributions on CelebA, SVHN, and CIFAR-100, and produce samples and reconstructions with high visual fidelity.

* 10 pages, 7 figures, 3 tables 

  Click for Model/Code and Paper
Generative and Discriminative Voxel Modeling with Convolutional Neural Networks

Aug 16, 2016
Andrew Brock, Theodore Lim, J. M. Ritchie, Nick Weston

When working with three-dimensional data, choice of representation is key. We explore voxel-based models, and present evidence for the viability of voxellated representations in applications including shape modeling and object classification. Our key contributions are methods for training voxel-based variational autoencoders, a user interface for exploring the latent space learned by the autoencoder, and a deep convolutional neural network architecture for object classification. We address challenges unique to voxel-based representations, and empirically evaluate our models on the ModelNet benchmark, where we demonstrate a 51.5% relative improvement in the state of the art for object classification.

* 9 pages, 5 figures, 2 tables 

  Click for Model/Code and Paper
Implicit Weight Uncertainty in Neural Networks

May 25, 2018
Nick Pawlowski, Andrew Brock, Matthew C. H. Lee, Martin Rajchl, Ben Glocker

Modern neural networks tend to be overconfident on unseen, noisy or incorrectly labelled data and do not produce meaningful uncertainty measures. Bayesian deep learning aims to address this shortcoming with variational approximations (such as Bayes by Backprop or Multiplicative Normalising Flows). However, current approaches have limitations regarding flexibility and scalability. We introduce Bayes by Hypernet (BbH), a new method of variational approximation that interprets hypernetworks as implicit distributions. It naturally uses neural networks to model arbitrarily complex distributions and scales to modern deep learning architectures. In our experiments, we demonstrate that our method achieves competitive accuracies and predictive uncertainties on MNIST and a CIFAR5 task, while being the most robust against adversarial attacks.

* Submitted to NIPS 2018, under review 

  Click for Model/Code and Paper
Victory Probability in the Fire Emblem Arena

Aug 29, 2018
Andrew Brockmann

We demonstrate how to efficiently compute the probability of victory in Fire Emblem arena battles. The probability can be expressed in terms of a multivariate recurrence relation which lends itself to a straightforward dynamic programming solution. Some implementation issues are addressed, and a full implementation is provided in code.

* 14 pages, 2 figures 

  Click for Model/Code and Paper
A Systematic Classification of Knowledge, Reasoning, and Context within the ARC Dataset

Jun 01, 2018
Michael Boratko, Harshit Padigela, Divyendra Mikkilineni, Pritish Yuvraj, Rajarshi Das, Andrew McCallum, Maria Chang, Achille Fokoue-Nkoutche, Pavan Kapanipathi, Nicholas Mattei, Ryan Musa, Kartik Talamadupula, Michael Witbrock

The recent work of Clark et al. introduces the AI2 Reasoning Challenge (ARC) and the associated ARC dataset that partitions open domain, complex science questions into an Easy Set and a Challenge Set. That paper includes an analysis of 100 questions with respect to the types of knowledge and reasoning required to answer them; however, it does not include clear definitions of these types, nor does it offer information about the quality of the labels. We propose a comprehensive set of definitions of knowledge and reasoning types necessary for answering the questions in the ARC dataset. Using ten annotators and a sophisticated annotation interface, we analyze the distribution of labels across the Challenge Set and statistics related to them. Additionally, we demonstrate that although naive information retrieval methods return sentences that are irrelevant to answering the query, sufficient supporting text is often present in the (ARC) corpus. Evaluating with human-selected relevant sentences improves the performance of a neural machine comprehension model by 42 points.

* Presented at the Machine Reading for Question Answering (MRQA 2018) Workshop at the 55th Annual Meeting of the Association for Computational Linguistics (ACL 2018). 11 pages, 5 tables, 4 figures 

  Click for Model/Code and Paper