Scholar's Hub

Based on the published evidence, the characteristics of COVID‐19 are systematically discussed in the hope of providing a reference for future studies and help for the prevention and control of the CO VID‐19 epidemic.

The incubation period falls within the range of 2-14 days with 95% confidence and has a mean of around 5 days when approximated using the best-fit lognormal distribution and it is recommended that the length of quarantine should be at least 14 days.

A new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely is proposed, which generalizes well to other tasks by applying it successfully to English constituency parsing both with large and limited training data.

A new language representation model, BERT, designed to pre-train deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers, which can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks.

This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.

GPT-3 achieves strong performance on many NLP datasets, including translation, question-answering, and cloze tasks, as well as several tasks that require on-the-fly reasoning or domain adaptation, such as unscrambling words, using a novel word in a sentence, or performing 3-digit arithmetic.

This review considers recent findings regarding GC action and generates criteria for determining whether a particular GC action permits, stimulates, or suppresses an ongoing stress-response or, as an additional category, is preparative for a subsequent stressor.

The 2(-Delta Delta C(T)) method is a convenient way to analyze the relative changes in gene expression from real-time quantitative PCR experiments and two variations of the method are presented that may be useful in the analysis of real- time, quantitative PCR data.

Experiments on three large language models show that chain-of-thought prompting improves performance on a range of arithmetic, commonsense, and symbolic reasoning tasks.

SARS-CoV-2 infection can be confirmed based on the patient’s history, clinical manifestations, imaging characteristics, and laboratory tests, including chest CT imaging features of the COVID-19 pneumonia.

The results show that fine-tuning with human feedback is a promising direction for aligning language models with human intent and showing improvements in truthfulness and reductions in toxic output generation while having minimal performance regressions on public NLP datasets.

Vision Transformer (ViT) attains excellent results compared to state-of-the-art convolutional networks while requiring substantially fewer computational resources to train.

It is demonstrated that the simple pre-training task of predicting which caption goes with which image is an efficient and scalable way to learn SOTA image representations from scratch on a dataset of 400 million (image, text) pairs collected from the internet.

In his Perspective, Sapolsky argues that the underlying causal agent may be glucocorticoids secreted in abnormally high amounts under stressful conditions.

A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective.

This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.

It is demonstrated that language models begin to learn these tasks without any explicit supervision when trained on a new dataset of millions of webpages called WebText, suggesting a promising path towards building language processing systems which learn to perform tasks from their naturally occurring demonstrations.

This systematic study compares pre-training objectives, architectures, unlabeled datasets, transfer approaches, and other factors on dozens of language understanding tasks and achieves state-of-the-art results on many benchmarks covering summarization, question answering, text classification, and more.

Evidence suggests that the glucocorticoid- and stress-related cognitive impairments involving declarative memory are probably related to the changes they effect in the hippocampus, whereas the stress-induced catecholamine effects on emotionally laden memories are postulated to involve structures such as the amgydala.

A new framework for estimating generative models via an adversarial process, in which two models are simultaneously train: a generative model G that captures the data distribution and a discriminative model D that estimates the probability that a sample came from the training data rather than G.

It is shown that composition of data augmentations plays a critical role in defining effective predictive tasks, and introducing a learnable nonlinear transformation between the representation and the contrastive loss substantially improves the quality of the learned representations, and contrastive learning benefits from larger batch sizes and more training steps compared to supervised learning.

Important innovations include the development of novel software architectures, the creation of a custom Urban Challenge simulator, and total commitment to JAUS to enable cross-platform compatibility.

Low-Rank Adaptation, or LoRA, is proposed, which freezes the pre-trained model weights and injects trainable rank decomposition matrices into each layer of the Transformer architecture, greatly reducing the number of trainable parameters for downstream tasks.

It is found that BERT was significantly undertrained, and can match or exceed the performance of every model published after it, and the best model achieves state-of-the-art results on GLUE, RACE and SQuAD.

This special issue is focused on the latest results in the area of IoT, with a focus on code division multiple access/pulse position modulation ultra-wideband radio frequency identification for Internet of Things and an effective Medium Access Control protocol.

It is conjecture that the use of a fixed-length vector is a bottleneck in improving the performance of this basic encoder-decoder architecture, and it is proposed to extend this by allowing a model to automatically (soft-)search for parts of a source sentence that are relevant to predicting a target word, without having to form these parts as a hard segment explicitly.

This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.

The general task-agnostic model outperforms discriminatively trained models that use architectures specifically crafted for each task, improving upon the state of the art in 9 out of the 12 tasks studied.