Related papers: Cold Case: The Lost MNIST Digits

Simulation studies are commonly used in methodological research for the empirical evaluation of data analysis methods. They generate artificial data sets under specified mechanisms and compare the performance of methods across conditions.…

Dataset distillation (DD) enhances training efficiency and reduces bandwidth by condensing large datasets into smaller synthetic ones. It enables models to achieve performance comparable to those trained on the raw full dataset and has…

The ability to learn different tasks sequentially is essential to the development of artificial intelligence. In general, neural networks lack this capability, the major obstacle being catastrophic forgetting. It occurs when the…

Optimising discrete data for a desired characteristic using gradient-based methods involves projecting the data into a continuous latent space and carrying out optimisation in this space. Carrying out global optimisation is difficult as…

This review aims to provide a comprehensive update on the progress made on the Sequential Testing problem (STP) in the last 20 years after the review, [1] was published. Many studies have provided new theoretical results, extensions of the…

We have developed MatGD (Material Graph Digitizer), which is a tool for digitizing a data line from scientific graphs. The algorithm behind the tool consists of four steps: (1) identifying graphs within subfigures, (2) separating axes and…

LSTMs have a proven track record in analyzing sequential data. But what about unordered instance bags, as found under a Multiple Instance Learning (MIL) setting? While not often used for this, we show LSTMs excell under this setting too. In…

Nonnegative matrix factorization (NMF) has attracted much attention in the last decade as a dimension reduction method in many applications. Due to the explosion in the size of data, naturally the samples are collected and stored…

The rapid evolution of deep neural networks has revolutionized the field of machine learning, enabling remarkable advancements in various domains. In this article, we introduce NeuroWrite, a unique method for predicting the categorization…

We integrate the recently proposed spatial transformer network (SPN) [Jaderberg et. al 2015] into a recurrent neural network (RNN) to form an RNN-SPN model. We use the RNN-SPN to classify digits in cluttered MNIST sequences. The proposed…

Nine popular clustering methods are applied to 42 real data sets. The aim is to give a detailed characterisation of the methods by means of several cluster validation indexes that measure various individual aspects of the resulting clusters…

Recently, Saeb et al (2017) showed that, in diagnostic machine learning applications, having data of each subject randomly assigned to both training and test sets (record-wise data split) can lead to massive underestimation of the…

In many fields of experimental science, papers that failed to replicate continue to be cited as a result of the poor discoverability of replication studies. As a first step to creating a system that automatically finds replication studies…

Training speech translation (ST) models requires large and high-quality datasets. MuST-C is one of the most widely used ST benchmark datasets. It contains around 400 hours of speech-transcript-translation data for each of the eight…

Quantifying the similarity of two or more datasets has widespread applications in statistics and machine learning. The method choice is, however, difficult due to the abundance of proposed methods and the lack of neutral comparison studies,…

Dataset distillation (DD) aims to minimize the time and memory consumption needed for training deep neural networks on large datasets, by creating a smaller synthetic dataset that has similar performance to that of the full real dataset.…

Reproducibility, the ability to reproduce the results of published papers or studies using their computer code and data, is a cornerstone of reliable scientific methodology. Studies where results cannot be reproduced by the scientific…

Multiple Instance Learning (MIL) is a weak supervision learning paradigm that allows modeling of machine learning problems in which labels are available only for groups of examples called bags. A positive bag may contain one or more…

Gorman and Bedrick (2019) argued for using random splits rather than standard splits in NLP experiments. We argue that random splits, like standard splits, lead to overly optimistic performance estimates. We can also split data in biased or…

NLP models have progressed drastically in recent years, according to numerous datasets proposed to evaluate performance. Questions remain, however, about how particular dataset design choices may impact the conclusions we draw about model…