手机等边缘设备上的微调模型将对敏感数据实现隐私的个性化。但是，在历史上，Edge训练仅限于具有简单体系结构的相对较小的模型，因为训练既是记忆力和能量密集型的。我们提出了诗人，这是一种算法，可以在存储器筛分的边缘设备上训练大型神经网络。诗人共同优化了重新布置和分页的综合搜索搜索空间，这两种算法可减少返回传播的记忆消耗。鉴于记忆预算和运行时间的限制，我们制定了一项混合成员线性计划（MILP），以进行最佳培训。我们的方法使培训能够在嵌入式设备上显着更大的模型，同时减少能源消耗，同时不修改反向传播的数学正确性。我们证明，可以在皮质类嵌入式设备的内存约束中微调RESNET-18和BERT，同时在能源效率方面的当前边缘训练方法的表现。诗人是一个开源项目，网址为https://github.com/shishirpatil/poet

问题回答模型努力推广到训练模式的新型组成，诸如更长的序列或更复杂的测试结构。目前的端到端模型学习扁平输入嵌入，可以丢失输入语法上下文。先前的方法通过学习置换不变模型来改善泛化，但这些方法不会扩展到更复杂的火车测试分裂。我们提出了接地的图形解码，一种通过与注意机制接地结构化预测来提高语言表示的组成概括的方法。接地使模型能够从输入中保留语法信息，从而显着提高复杂输入的泛化。通过预测包含查询条件的连词的结构化图，我们学习一个组不变的表示，而不会在目标域上做出假设。我们的模型显着优于现有的基础基础上的组成自由BASE问题（CFQ）数据集，这是一个有挑战性的基准，用于有问题的合成概括。此外，我们有效地解决了98％精度的MCD1分体式。

最近的工作通过从上下文重建令牌来了解源代码的上下文表示。对于诸如英语中汇总代码的下游语义理解任务，这些表示应该理想地捕获程序功能。但是，我们表明流行的基于重建的BERT模型对源代码编辑敏感，即使编辑保存语义。我们提出了僵局：一种学习代码功能的对比预训练任务，而不是形成。触发预先训练神经网络，以识别许多不等效的干扰者之间的程序的功能类似的变体。我们使用自动源到源编译器作为数据增强的形式来缩放可扩展这些变体。对比预训练将JavaScript摘要和打字类型推理准确性提高2％至13％。我们还提出了一个新的零拍摄JavaScript代码克隆检测数据集，显示施加均比更强大和语义有意义。就此而言，我们以39％的Auroc在普发的环境中以39％的AUROC倾斜，高达5％的自然代码。

Multiple studies have focused on predicting the prospective popularity of an online document as a whole, without paying attention to the contributions of its individual parts. We introduce the task of proactively forecasting popularities of sentences within online news documents solely utilizing their natural language content. We model sentence-specific popularity forecasting as a sequence regression task. For training our models, we curate InfoPop, the first dataset containing popularity labels for over 1.7 million sentences from over 50,000 online news documents. To the best of our knowledge, this is the first dataset automatically created using streams of incoming search engine queries to generate sentence-level popularity annotations. We propose a novel transfer learning approach involving sentence salience prediction as an auxiliary task. Our proposed technique coupled with a BERT-based neural model exceeds nDCG values of 0.8 for proactive sentence-specific popularity forecasting. Notably, our study presents a non-trivial takeaway: though popularity and salience are different concepts, transfer learning from salience prediction enhances popularity forecasting. We release InfoPop and make our code publicly available: https://github.com/sayarghoshroy/InfoPopularity

Speech systems are sensitive to accent variations. This is especially challenging in the Indian context, with an abundance of languages but a dearth of linguistic studies characterising pronunciation variations. The growing number of L2 English speakers in India reinforces the need to study accents and L1-L2 interactions. We investigate the accents of Indian English (IE) speakers and report in detail our observations, both specific and common to all regions. In particular, we observe the phonemic variations and phonotactics occurring in the speakers' native languages and apply this to their English pronunciations. We demonstrate the influence of 18 Indian languages on IE by comparing the native language pronunciations with IE pronunciations obtained jointly from existing literature studies and phonetically annotated speech of 80 speakers. Consequently, we are able to validate the intuitions of Indian language influences on IE pronunciations by justifying pronunciation rules from the perspective of Indian language phonology. We obtain a comprehensive description in terms of universal and region-specific characteristics of IE, which facilitates accent conversion and adaptation of existing ASR and TTS systems to different Indian accents.

In molecular research, simulation \& design of molecules are key areas with significant implications for drug development, material science, and other fields. Current classical computational power falls inadequate to simulate any more than small molecules, let alone protein chains on hundreds of peptide. Therefore these experiment are done physically in wet-lab, but it takes a lot of time \& not possible to examine every molecule due to the size of the search area, tens of billions of dollars are spent every year in these research experiments. Molecule simulation \& design has lately advanced significantly by machine learning models, A fresh perspective on the issue of chemical synthesis is provided by deep generative models for graph-structured data. By optimising differentiable models that produce molecular graphs directly, it is feasible to avoid costly search techniques in the discrete and huge space of chemical structures. But these models also suffer from computational limitations when dimensions become huge and consume huge amount of resources. Quantum Generative machine learning in recent years have shown some empirical results promising significant advantages over classical counterparts.

Developing and least developed countries face the dire challenge of ensuring that each child in their country receives required doses of vaccination, adequate nutrition and proper medication. International agencies such as UNICEF, WHO and WFP, among other organizations, strive to find innovative solutions to determine which child has received the benefits and which have not. Biometric recognition systems have been sought out to help solve this problem. To that end, this report establishes a baseline accuracy of a commercial contactless palmprint recognition system that may be deployed for recognizing children in the age group of one to five years old. On a database of contactless palmprint images of one thousand unique palms from 500 children, we establish SOTA authentication accuracy of 90.85% @ FAR of 0.01%, rank-1 identification accuracy of 99.0% (closed set), and FPIR=0.01 @ FNIR=0.3 for open-set identification using PalmMobile SDK from Armatura.

Selective classification involves identifying the subset of test samples that a model can classify with high accuracy, and is important for applications such as automated medical diagnosis. We argue that this capability of identifying uncertain samples is valuable for training classifiers as well, with the aim of building more accurate classifiers. We unify these dual roles by training a single auxiliary meta-network to output an importance weight as a function of the instance. This measure is used at train time to reweight training data, and at test-time to rank test instances for selective classification. A second, key component of our proposal is the meta-objective of minimizing dropout variance (the variance of classifier output when subjected to random weight dropout) for training the metanetwork. We train the classifier together with its metanetwork using a nested objective of minimizing classifier loss on training data and meta-loss on a separate meta-training dataset. We outperform current state-of-the-art on selective classification by substantial margins--for instance, upto 1.9% AUC and 2% accuracy on a real-world diabetic retinopathy dataset. Finally, our meta-learning framework extends naturally to unsupervised domain adaptation, given our unsupervised variance minimization meta-objective. We show cumulative absolute gains of 3.4% / 3.3% accuracy and AUC over the other baselines in domain shift settings on the Retinopathy dataset using unsupervised domain adaptation.

Many real-world learning scenarios face the challenge of slow concept drift, where data distributions change gradually over time. In this setting, we pose the problem of learning temporally sensitive importance weights for training data, in order to optimize predictive accuracy. We propose a class of temporal reweighting functions that can capture multiple timescales of change in the data, as well as instance-specific characteristics. We formulate a bi-level optimization criterion, and an associated meta-learning algorithm, by which these weights can be learned. In particular, our formulation trains an auxiliary network to output weights as a function of training instances, thereby compactly representing the instance weights. We validate our temporal reweighting scheme on a large real-world dataset of 39M images spread over a 9 year period. Our extensive experiments demonstrate the necessity of instance-based temporal reweighting in the dataset, and achieve significant improvements to classical batch-learning approaches. Further, our proposal easily generalizes to a streaming setting and shows significant gains compared to recent continual learning methods.

Intelligently extracting and linking complex scientific information from unstructured text is a challenging endeavor particularly for those inexperienced with natural language processing. Here, we present a simple sequence-to-sequence approach to joint named entity recognition and relation extraction for complex hierarchical information in scientific text. The approach leverages a pre-trained large language model (LLM), GPT-3, that is fine-tuned on approximately 500 pairs of prompts (inputs) and completions (outputs). Information is extracted either from single sentences or across sentences in abstracts/passages, and the output can be returned as simple English sentences or a more structured format, such as a list of JSON objects. We demonstrate that LLMs trained in this way are capable of accurately extracting useful records of complex scientific knowledge for three representative tasks in materials chemistry: linking dopants with their host materials, cataloging metal-organic frameworks, and general chemistry/phase/morphology/application information extraction. This approach represents a simple, accessible, and highly-flexible route to obtaining large databases of structured knowledge extracted from unstructured text. An online demo is available at http://www.matscholar.com/info-extraction.