Simple (philosophy)
View article: Evaluating the Effectiveness of Large Language Models in Representing Textual Descriptions of Geometry and Spatial Relations (Short Paper)
Evaluating the Effectiveness of Large Language Models in Representing Textual Descriptions of Geometry and Spatial Relations (Short Paper) Open
This research focuses on assessing the ability of large language models (LLMs) in representing geometries and their spatial relations. We utilize LLMs including GPT-2 and BERT to encode the well-known text (WKT) format of geometries and th…
View article
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications Open
We present a class of efficient models called MobileNets for mobile and embedded vision applications. MobileNets are based on a streamlined architecture that uses depth-wise separable convolutions to build light weight deep neural networks…
View article
Joint effect of ageing and multilayer structure prevents ordering in the voter model Open
The voter model rules are simple, with agents copying the state of a random neighbor, but they lead to non-trivial dynamics. Besides opinion processes, the model has also applications for catalysis and species competition. Inspired by the …
View article
Least-Squares Means: The<i>R</i>Package<b>lsmeans</b> Open
Least-squares means are predictions from a linear model, or averages thereof. They are useful in the analysis of experimental data for summarizing the effects of factors, and for testing linear contrasts among predictions. The lsmeans pack…
View article
DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks Open
State-of-the-art deep neural networks have achieved impressive results on many image classification tasks. However, these same architectures have been shown to be unstable to small, well sought, perturbations of the images. Despite the imp…
View article
mixup: Beyond Empirical Risk Minimization Open
Large deep neural networks are powerful, but exhibit undesirable behaviors such as memorization and sensitivity to adversarial examples. In this work, we propose mixup, a simple learning principle to alleviate these issues. In essence, mix…
View article
Training language models to follow instructions with human feedback Open
Making language models bigger does not inherently make them better at following a user's intent. For example, large language models can generate outputs that are untruthful, toxic, or simply not helpful to the user. In other words, these m…
View article
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models Open
We explore how generating a chain of thought -- a series of intermediate reasoning steps -- significantly improves the ability of large language models to perform complex reasoning. In particular, we show how such reasoning abilities emerg…
View article
Simple Features for R: Standardized Support for Spatial Vector Data Open
Simple features are a standardized way of encoding spatial vector data (points, lines, polygons) in computers.The sf package implements simple features in R, and has roughly the same capacity for spatial vector data as packages sp, rgeos, …
View article
Simple online and realtime tracking Open
This paper explores a pragmatic approach to multiple object tracking where the main focus is to associate objects efficiently for online and realtime applications. To this end, detection quality is identified as a key factor influencing tr…
View article
Language Models are Few-Shot Learners Open
Recent work has demonstrated substantial gains on many NLP tasks and benchmarks by pre-training on a large corpus of text followed by fine-tuning on a specific task. While typically task-agnostic in architecture, this method still requires…
View article
Axiomatic Attribution for Deep Networks Open
We study the problem of attributing the prediction of a deep network to its input features, a problem previously studied by several other works. We identify two fundamental axioms---Sensitivity and Implementation Invariance that attributio…
View article
SimCSE: Simple Contrastive Learning of Sentence Embeddings Open
This paper presents SimCSE, a simple contrastive learning framework that greatly advances the state-of-the-art sentence embeddings. We first describe an unsupervised approach, which takes an input sentence and predicts itself in a contrast…
View article
FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence Open
Semi-supervised learning (SSL) provides an effective means of leveraging unlabeled data to improve a model's performance. In this paper, we demonstrate the power of a simple combination of two common SSL methods: consistency regularization…
View article
Improved Baselines with Momentum Contrastive Learning Open
Contrastive unsupervised learning has recently shown encouraging progress, e.g., in Momentum Contrast (MoCo) and SimCLR. In this note, we verify the effectiveness of two of SimCLR's design improvements by implementing them in the MoCo fram…
View article
Neural Discrete Representation Learning. Open
Learning useful representations without supervision remains a key challenge in machine learning. In this paper, we propose a simple yet powerful generative model that learns such discrete representations. Our model, the Vector Quantised-Va…
View article
Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules. Open
We report a method to convert discrete representations of molecules to and from a multidimensional continuous representation. This model allows us to generate new molecules for efficient exploration and optimization through open-ended spac…
View article
Wide Residual Networks Open
Deep residual networks were shown to be able to scale up to thousands of layers and still have improving performance. However, each fraction of a percent of improved accuracy costs nearly doubling the number of layers, and so training very…
View article
Neural Discrete Representation Learning Open
Learning useful representations without supervision remains a key challenge in machine learning. In this paper, we propose a simple yet powerful generative model that learns such discrete representations. Our model, the Vector Quantised-Va…
View article
SMS: Smart Model Selection in PhyML Open
Model selection using likelihood-based criteria (e.g., AIC) is one of the first steps in phylogenetic analysis. One must select both a substitution matrix and a model for rates across sites. A simple method is to test all combinations and …
View article
Repeated Measures Correlation Open
Repeated measures correlation (rmcorr) is a statistical technique for determining the common within-individual association for paired measures assessed on two or more occasions for multiple individuals. Simple regression/correlation is oft…
View article
Return of Frustratingly Easy Domain Adaptation Open
Unlike human learning, machine learning often fails to handle changes between training (source) and test (target) input distributions. Such domain shifts, common in practical scenarios, severely damage the performance of conventional machi…
View article
On Calibration of Modern Neural Networks Open
Confidence calibration -- the problem of predicting probability estimates representative of the true correctness likelihood -- is important for classification models in many applications. We discover that modern neural networks, unlike tho…
View article
Deep Mutual Learning Open
Model distillation is an effective and widely used technique to transfer knowledge from a teacher to a student network. The typical application is to transfer from a powerful large network or ensemble to a small network, in order to meet t…
View article
Progressive Growing of GANs for Improved Quality, Stability, and Variation Open
We describe a new training methodology for generative adversarial networks. The key idea is to grow both the generator and discriminator progressively: starting from a low resolution, we add new layers that model increasingly fine details …
View article
Interaction Region Indicator: A Simple Real Space Function Clearly Revealing Both Chemical Bonds and Weak Interactions** Open
Graphically revealing interaction regions in a chemical system enables chemists to quickly recognize where significant interactions have formed. Reduced density gradient (RDG) has already been widely employed in literatures to visually exh…
View article
New tolerance factor to predict the stability of perovskite oxides and halides Open
Simple and interpretable data-driven descriptor accurately predicts the synthesizability of single and double perovskites.
View article
A critical analysis of the α, β and γ phases in poly(vinylidene fluoride) using FTIR Open
A universal but simple procedure for identifying the α, β and γ phases in PVDF using FTIR is proposed and validated. An integrated quantification methodology for individual β and γ phase in mixed systems is also proposed.
View article
Mask R-CNN Open
We present a conceptually simple, flexible, and general framework for object instance segmentation. Our approach efficiently detects objects in an image while simultaneously generating a high-quality segmentation mask for each instance. Th…
View article
Understanding the Limits of LoRaWAN Open
Low-power wide area networking technology offers long-range communication, which enables new types of services. Several solutions exist; LoRaWAN is arguably the most adopted. It promises ubiquitous connectivity in outdoor IoT applications,…