Lyndon White

Frank Schäfer, Mohamed Tarek, Lyndon White et al.

No single Automatic Differentiation (AD) system is the optimal choice for all problems. This means informed selection of an AD system and combinations can be a problem-specific variable that can greatly impact performance. In the Julia programming language, the major AD systems target the same input and thus in theory can compose. Hitherto, switching between AD packages in the Julia Language required end-users to familiarize themselves with the user-facing API of the respective packages. Furthermore, implementing a new, usable AD package required AD package developers to write boilerplate code to define convenience API functions for end-users. As a response to these issues, we present AbstractDifferentiation.jl for the automatized generation of an extensive, unified, user-facing API for any AD package. By splitting the complexity between AD users and AD developers, AD package developers only need to implement one or two primitive definitions to support various utilities for AD users like Jacobians, Hessians and lazy product operators from native primitives such as pullbacks or pushforwards, thus removing tedious -- but so far inevitable -- boilerplate code, and enabling the easy switching and composing between AD implementations for end-users.

Naeha Sharif, Lyndon White, Mohammed Bennamoun et al.

The area of automatic image caption evaluation is still undergoing intensive research to address the needs of generating captions which can meet adequacy and fluency requirements. Based on our past attempts at developing highly sophisticated learning-based metrics, we have discovered that a simple cosine similarity measure using the Mean of Word Embeddings(MOWE) of captions can actually achieve a surprisingly high performance on unsupervised caption evaluation. This inspires our proposed work on an effective metric WEmbSim, which beats complex measures such as SPICE, CIDEr and WMD at system-level correlation with human judgments. Moreover, it also achieves the best accuracy at matching human consensus scores for caption pairs, against commonly used unsupervised methods. Therefore, we believe that WEmbSim sets a new baseline for any complex metric to be justified.

Naeha Sharif, Lyndon White, Mohammed Bennamoun et al.

Automatic evaluation metrics hold a fundamental importance in the development and fine-grained analysis of captioning systems. While current evaluation metrics tend to achieve an acceptable correlation with human judgements at the system level, they fail to do so at the caption level. In this work, we propose a neural network-based learned metric to improve the caption-level caption evaluation. To get a deeper insight into the parameters which impact a learned metrics performance, this paper investigates the relationship between different linguistic features and the caption-level correlation of the learned metrics. We also compare metrics trained with different training examples to measure the variations in their evaluation. Moreover, we perform a robustness analysis, which highlights the sensitivity of learned and handcrafted metrics to various sentence perturbations. Our empirical analysis shows that our proposed metric not only outperforms the existing metrics in terms of caption-level correlation but it also shows a strong system-level correlation against human assessments.

Chris Rackauckas, Mike Innes, Yingbo Ma et al.

DiffEqFlux.jl is a library for fusing neural networks and differential equations. In this work we describe differential equations from the viewpoint of data science and discuss the complementary nature between machine learning models and differential equations. We demonstrate the ability to incorporate DifferentialEquations.jl-defined differential equation problems into a Flux-defined neural network, and vice versa. The advantages of being able to use the entire DifferentialEquations.jl suite for this purpose is demonstrated by counter examples where simple integration strategies fail, but the sophisticated integration strategies provided by the DifferentialEquations.jl library succeed. This is followed by a demonstration of delay differential equations and stochastic differential equations inside of neural networks. We show high-level functionality for defining neural ordinary differential equations (neural networks embedded into the differential equation) and describe the extra models in the Flux model zoo which includes neural stochastic differential equations. We conclude by discussing the various adjoint methods used for backpropogation of the differential equation solvers. DiffEqFlux.jl is an important contribution to the area, as it allows the full weight of the differential equation solvers developed from decades of research in the scientific computing field to be readily applied to the challenges posed by machine learning and data science.

Lyndon White, Roberto Togneri, Wei Liu et al.

We present DataDeps.jl: a julia package for the reproducible handling of static datasets to enhance the repeatability of scripts used in the data and computational sciences. It is used to automate the data setup part of running software which accompanies a paper to replicate a result. This step is commonly done manually, which expends time and allows for confusion. This functionality is also useful for other packages which require data to function (e.g. a trained machine learning based model). DataDeps.jl simplifies extending research software by automatically managing the dependencies and makes it easier to run another author's code, thus enhancing the reproducibility of data science research.

Lyndon White, Roberto Togneri, Wei Liu et al.

Color names are often made up of multiple words. As a task in natural language understanding we investigate in depth the capacity of neural networks based on sums of word embeddings (SOWE), recurrence (LSTM and GRU based RNNs) and convolution (CNN), to estimate colors from sequences of terms. We consider both point and distribution estimates of color. We argue that the latter has a particular value as there is no clear agreement between people as to what a particular color describes -- different people have a different idea of what it means to be ``very dark orange'', for example. Surprisingly, despite it's simplicity, the sum of word embeddings generally performs the best on almost all evaluations.