Stochastic gradient descent plays a fundamental role in nearly all applications of deep learning. However its ability to converge to a global minimum remains shrouded in mystery. In this paper we propose to study the behavior of the loss function on fixed mini-batches along SGD trajectories. We show that the loss function on a fixed batch appears to be remarkably convex-like. In particular for ResNet the loss for any fixed mini-batch can be accurately modeled by a quadratic function and a very low loss value can be reached in just one step of gradient descent with sufficiently large learning rate. We propose a simple model that allows to analyze the relationship between the gradients of stochastic mini-batches and the full batch. Our analysis allows us to discover the equivalency between iterate aggregates and specific learning rate schedules. In particular, for Exponential Moving Average (EMA) and Stochastic Weight Averaging we show that our proposed model matches the observed training trajectories on ImageNet. Our theoretical model predicts that an even simpler averaging technique, averaging just two points a many steps apart, significantly improves accuracy compared to the baseline. We validated our findings on ImageNet and other datasets using ResNet architecture.

In recent years Generative Machine Learning systems have advanced significantly. A current wave of generative systems use text prompts to create complex imagery, video, even 3D datasets. The creators of these systems claim a revolution in bringing creativity and art to anyone who can type a prompt. In this position paper, we question the basis for these claims, dividing our analysis into three areas: the limitations of linguistic descriptions, implications of the dataset, and lastly, matters of materiality and embodiment. We conclude with an analysis of the creative possibilities enabled by prompt-based systems, asking if they can be considered a new artistic medium.

We introduce HunSum-1: a dataset for Hungarian abstractive summarization, consisting of 1.14M news articles. The dataset is built by collecting, cleaning and deduplicating data from 9 major Hungarian news sites through CommonCrawl. Using this dataset, we build abstractive summarizer models based on huBERT and mT5. We demonstrate the value of the created dataset by performing a quantitative and qualitative analysis on the models' results. The HunSum-1 dataset, all models used in our experiments and our code are available open source.

Neural language models (LMs) are arguably less data-efficient than humans -- why does this gap occur? In this study, we hypothesize that this gap stems from the learners' accessibility to modalities other than text, specifically, vision. We conducted two complementary experiments (using noisy, realistic data and a simplified, artificial one) toward the advantage of vision in the syntactic generalization of LMs. Our results showed that vision accelerated a proper linguistic generalization in the simplified, artificial setting, but LMs struggled with the noisy, realistic setting. These mixed results indicate several possibilities, e.g., vision can potentially boost language acquisition, but learners' additional visual/linguistic prior knowledge should be needed to robustly make use of raw images for efficient language acquisition.

Nowadays, many researchers are focusing their attention on the subject of machine translation (MT). However, Persian machine translation has remained unexplored despite a vast amount of research being conducted in languages with high resources, such as English. Moreover, while a substantial amount of research has been undertaken in statistical machine translation for some datasets in Persian, there is currently no standard baseline for transformer-based text2text models on each corpus. This study collected and analysed the most popular and valuable parallel corpora, which were used for Persian-English translation. Furthermore, we fine-tuned and evaluated two state-of-the-art attention-based seq2seq models on each dataset separately (48 results). We hope this paper will assist researchers in comparing their Persian to English and vice versa machine translation results Figure 1: Transformer model architecture to a standard baseline.

A number of labeling systems based on text have been proposed to help monitor work on the United Nations (UN) Sustainable Development Goals (SDGs). Here, we present a systematic comparison of systems using a variety of text sources and show that systems differ considerably in their specificity (i.e., true-positive rate) and sensitivity (i.e., true-negative rate), have systematic biases (e.g., are more sensitive to specific SDGs relative to others), and are susceptible to the type and amount of text analyzed. We then show that an ensemble model that pools labeling systems alleviates some of these limitations, exceeding the labeling performance of all currently available systems. We conclude that researchers and policymakers should care about the choice of labeling system and that ensemble methods should be favored when drawing conclusions about the absolute and relative prevalence of work on the SDGs based on automated methods.

The Robert C. Byrd Green Bank Telescope in West Virginia is one of several helping to search for alien civilizations.Credit: Jim West/Alamy From the hills of West Virginia to the flats of rural Australia, some of the world's largest telescopes are listening for signals from distant alien civilizations. The search for extraterrestrial intelligence, known as SETI, is an effort to find artificial-looking electromagnetic radiation that might have come from a technologically advanced civilization in a far-away solar system. A study published today1 describes one of several efforts to use machine learning, a subset of artificial intelligence (AI), to help astronomers sift quickly through the reams of data such searches yield. As AI reshapes many scientific fields, what promise does it hold for the search for life beyond Earth? "It is a new era for SETI research that is opening up thanks to machine learning technology," says Franck Marchis, a planetary astronomer at the SETI Institute in Mountain View, California.

In earthquake-prone zones, the seismic performance of reinforced concrete cantilever (RCC) retaining walls is significant. In this study, the seismic performance was investigated using horizontal and vertical pseudo-static coefficients. To tackle RCC weights and forces resulting from these earth pressures, 26 constraints for structural strengths and geotechnical stability along with 12 geometric variables are associated with each design. These constraints and design variables form a constraint optimization problem with a twelve-dimensional solution space. To conduct effective search and produce sustainable, economical, lightweight RCC designs robust against earthquake hazards, a novel adaptive fuzzy-based metaheuristic algorithm is applied. The proposed method divides the search space to sub-regions and establishes exploration, information sharing, and exploitation search capabilities based on its novel search components. Further, fuzzy inference systems were employed to address parameterization and computational cost evaluation issues. It was found that the proposed algorithm can achieve low-cost, low-weight, and low CO2 emission RCC designs under nine seismic conditions in comparison with several classical and best-performing design optimizers.

A significant body of recent research in the field of Learning Analytics has focused on leveraging machine learning approaches for predicting at-risk students in order to initiate timely interventions and thereby elevate retention and completion rates. The overarching feature of the majority of these research studies has been on the science of prediction only. The component of predictive analytics concerned with interpreting the internals of the models and explaining their predictions for individual cases to stakeholders has largely been neglected. Additionally, works that attempt to employ data-driven prescriptive analytics to automatically generate evidence-based remedial advice for at-risk learners are in their infancy. eXplainable AI is a field that has recently emerged providing cutting-edge tools which support transparent predictive analytics and techniques for generating tailored advice for at-risk students. This study proposes a novel framework that unifies both transparent machine learning as well as techniques for enabling prescriptive analytics, while integrating the latest advances in large language models. This work practically demonstrates the proposed framework using predictive models for identifying at-risk learners of programme non-completion. The study then further demonstrates how predictive modelling can be augmented with prescriptive analytics on two case studies in order to generate human-readable prescriptive feedback for those who are at risk using ChatGPT.

The study of Neural Tangent Kernels (NTKs) has provided much needed insight into convergence and generalization properties of neural networks in the over-parametrized (wide) limit by approximating the network using a first-order Taylor expansion with respect to its weights in the neighborhood of their initialization values. This allows neural network training to be analyzed from the perspective of reproducing kernel Hilbert spaces (RKHS), which is informative in the over-parametrized regime, but a poor approximation for narrower networks as the weights change more during training. Our goal is to extend beyond the limits of NTK toward a more general theory. We construct an exact power-series representation of the neural network in a finite neighborhood of the initial weights as an inner product of two feature maps, respectively from data and weight-step space, to feature space, allowing neural network training to be analyzed from the perspective of reproducing kernel {\em Banach} space (RKBS). We prove that, regardless of width, the training sequence produced by gradient descent can be exactly replicated by regularized sequential learning in RKBS. Using this, we present novel bound on uniform convergence where the iterations count and learning rate play a central role, giving new theoretical insight into neural network training.