Christopher Beckham
YOU?
Author Swipe
View article: DStruct2Design: Data and Benchmarks for Data Structure Driven Generative Floor Plan Design
DStruct2Design: Data and Benchmarks for Data Structure Driven Generative Floor Plan Design Open
Text conditioned generative models for images have yielded impressive results. Text conditioned floorplan generation as a special type of raster image generation task also received particular attention. However there are many use cases in …
View article: Long-Term Camelid Husbandry and Agricultural Intensification in the Southern Nasca Region, Peru: Insight from Faunal Isotopes
Long-Term Camelid Husbandry and Agricultural Intensification in the Southern Nasca Region, Peru: Insight from Faunal Isotopes Open
We examined stable isotopes (δ 13 C, δ 15 N, and δ 34 S) of camelid, cavid, and cervid remains from Upanca, an archaeological site located in the Southern Nasca Region on the south coast of Peru. Occupation at the site began in the Middle …
View article: Parallel-mentoring for Offline Model-based Optimization
Parallel-mentoring for Offline Model-based Optimization Open
We study offline model-based optimization to maximize a black-box objective function with a static dataset of designs and scores. These designs encompass a variety of domains, including materials, robots and DNA sequences. A common approac…
View article: Conservative objective models are a special kind of contrastive divergence-based energy model
Conservative objective models are a special kind of contrastive divergence-based energy model Open
In this work we theoretically show that conservative objective models (COMs) for offline model-based optimisation (MBO) are a special kind of contrastive divergence-based energy model, one where the energy function represents both the unco…
View article: Score-based Diffusion Models in Function Space
Score-based Diffusion Models in Function Space Open
Diffusion models have recently emerged as a powerful framework for generative modeling. They consist of a forward process that perturbs input data with Gaussian white noise and a reverse process that learns a score function to generate sam…
View article: Defending Intellectual Work in Schools
Defending Intellectual Work in Schools Open
In an era marked by change in American schools, Professor William C. Bagley (1873–1946) defended traditional education. Contra the work of educational progressivists such as John Dewey who sought to rid schools of rote memorization and boo…
View article: Visual Question Answering From Another Perspective: CLEVR Mental Rotation Tests
Visual Question Answering From Another Perspective: CLEVR Mental Rotation Tests Open
Different types of mental rotation tests have been used extensively in psychology to understand human visual reasoning and perception. Understanding what an object or visual scene would look like from another viewpoint is a challenging pro…
View article: Exploring validation metrics for offline model-based optimisation with diffusion models
Exploring validation metrics for offline model-based optimisation with diffusion models Open
In model-based optimisation (MBO) we are interested in using machine learning to design candidates that maximise some measure of reward with respect to a black box function called the (ground truth) oracle, which is expensive to compute si…
View article: Overcoming challenges in leveraging GANs for few-shot data augmentation
Overcoming challenges in leveraging GANs for few-shot data augmentation Open
In this paper, we explore the use of GAN-based few-shot data augmentation as a method to improve few-shot classification performance. We perform an exploration into how a GAN can be fine-tuned for such a task (one of which is in a class-in…
View article: Towards annotation-efficient segmentation via image-to-image translation
Towards annotation-efficient segmentation via image-to-image translation Open
Often in medical imaging, it is prohibitively challenging to produce enough boundary annotations to train deep neural networks for accurate tumor segmentation. We propose the use of weak labels about whether an image presents tumor or whet…
View article: Towards semi-supervised segmentation via image-to-image translation
Towards semi-supervised segmentation via image-to-image translation Open
In many cases, especially with medical images, it is prohibitively challenging to produce a sufficiently large training sample of pixel-level annotations to train deep neural networks for semantic image segmentation. On the other hand, som…
View article: Adversarial Mixup Resynthesizers
Adversarial Mixup Resynthesizers Open
In this paper, we explore new approaches to combining information encoded within the learned representations of autoencoders. We explore models that are capable of combining the attributes of multiple inputs such that a resynthesised outpu…
View article: On Adversarial Mixup Resynthesis
On Adversarial Mixup Resynthesis Open
In this paper, we explore new approaches to combining information encoded within the learned representations of auto-encoders. We explore models that are capable of combining the attributes of multiple inputs such that a resynthesised outp…
View article: Manifold Mixup: Better Representations by Interpolating Hidden States
Manifold Mixup: Better Representations by Interpolating Hidden States Open
Deep neural networks excel at learning the training data, but often provide incorrect and confident predictions when evaluated on slightly different test examples. This includes distribution shifts, outliers, and adversarial examples. To a…
View article: Manifold Mixup: Encouraging Meaningful On-Manifold Interpolation as a Regularizer.
Manifold Mixup: Encouraging Meaningful On-Manifold Interpolation as a Regularizer. Open
Deep networks often perform well on the data manifold on which they are trained, yet give incorrect (and often very confident) answers when evaluated on points from off of the training distribution. This is exemplified by the adversarial e…
View article: Unsupervised Depth Estimation, 3D Face Rotation and Replacement
Unsupervised Depth Estimation, 3D Face Rotation and Replacement Open
We present an unsupervised approach for learning to estimate three dimensional (3D) facial structure from a single image while also predicting 3D viewpoint transformations that match a desired pose and facial geometry. We achieve this by i…
View article: A step towards procedural terrain generation with GANs
A step towards procedural terrain generation with GANs Open
Procedural terrain generation for video games has been traditionally been done with smartly designed but handcrafted algorithms that generate heightmaps. We propose a first step toward the learning and synthesis of these using recent advan…
View article: Unimodal probability distributions for deep ordinal classification
Unimodal probability distributions for deep ordinal classification Open
Probability distributions produced by the cross-entropy loss for ordinal classification problems can possess undesired properties. We propose a straightforward technique to constrain discrete ordinal probability distributions to be unimoda…
View article: Semi-Supervised Detection of Extreme Weather Events in Large Climate Datasets
Semi-Supervised Detection of Extreme Weather Events in Large Climate Datasets Open
The detection and identification of extreme weather events in large scale climate simulations is an important problem for risk management, informing governmental policy decisions and advancing our basic understanding of the climate system.…
View article: ExtremeWeather: A large-scale climate dataset for semi-supervised detection, localization, and understanding of extreme weather events
ExtremeWeather: A large-scale climate dataset for semi-supervised detection, localization, and understanding of extreme weather events Open
Then detection and identification of extreme weather events in large-scale climate simulations is an important problem for risk management, informing governmental policy decisions and advancing our basic understanding of the climate system…
View article: A simple squared-error reformulation for ordinal classification
A simple squared-error reformulation for ordinal classification Open
In this paper, we explore ordinal classification (in the context of deep neural networks) through a simple modification of the squared error loss which not only allows it to not only be sensitive to class ordering, but also allows the poss…
View article: WekaPyScript: Classification, Regression, and Filter Schemes for WEKA Implemented in Python
WekaPyScript: Classification, Regression, and Filter Schemes for WEKA Implemented in Python Open
WekaPyScript is a package for the machine learning software WEKA that allows learning algorithms and preprocessing methods for classification and regression to be written in Python, as opposed to WEKA’s implementation language, Java. This …
View article: weka-pyscript: 0.4.1
weka-pyscript: 0.4.1 Open
Filter now has -stdout flag. y should now not exist in args if class attribute is not set (or if it is ignored).
View article: weka-pyscript: 0.4.0
weka-pyscript: 0.4.0 Open
Filter system has changed - instead of process() returning an ARFF, it simply returns args. Add ignore class functionality (ignore-class). Fix bug in instance_to_string where it was assumed instances were not regression ones.
View article: weka-pyscript: 0.2.1
weka-pyscript: 0.2.1 Open
Can now choose to save the script in the model using the -save flag.
View article: Classification and regression algorithms for WEKA implemented in Python
Classification and regression algorithms for WEKA implemented in Python Open
WEKA is a popular machine learning workbench written in Java that allows users to easily classify, process, and explore data. There are many ways WEKA can be used: through the WEKA Explorer, users can visualise data, train classifiers and …
View article: weka-pyscript: 0.1.1
weka-pyscript: 0.1.1 Open
WEKA classifier to execute arbitrary Python scripts
View article: weka-pyscript: 4sep-pre
weka-pyscript: 4sep-pre Open
Pre-release as of the 4th of September.