眼科图像和衍生物，例如视网膜神经纤维层（RNFL）厚度图对于检测和监测眼科疾病至关重要（例如，青光眼）。对于计算机辅助诊断眼疾病，关键技术是自动从眼科图像中提取有意义的特征，这些特征可以揭示与功能视觉丧失相关的生物标志物（例如RNFL变薄模式）。然而，将结构性视网膜损伤与人类视力丧失联系起来的眼科图像的表示，主要是由于患者之间的解剖学变化很大。在存在图像伪像的情况下，这项任务变得更加具有挑战性，由于图像采集和自动细分，这很常见。在本文中，我们提出了一个耐伪造的无监督的学习框架，该框架称为眼科图像的学习表示。 Eyelearn具有一个伪影校正模块，可以学习可以最好地预测无伪影眼镜图像的表示形式。此外，Eyelearn采用聚类引导的对比度学习策略，以明确捕获内部和间形的亲和力。在训练过程中，图像在簇中动态组织，以形成对比样品，其中鼓励在相同或不同的簇中分别学习相似或不同的表示形式。为了评估包冰者，我们使用青光眼患者的现实世界眼科摄影图数据集使用学习的表示形式进行视野预测和青光眼检测。广泛的实验和与最先进方法的比较验证了眼球从眼科图像中学习最佳特征表示的有效性。

在过去的几十年里，互联网用户在网上举办了实时事件并与现场，互动受众分享经历的日益增长的需求。像抽搐一样的在线流媒体服务吸引了数百万用户来流并窥视。关于抽搐对流动性普及的预测有很少的研究。在本文中，我们看起来可能有助于娱乐的潜在因素。在4周时段期间，通过使用Twitch的API一致的跟踪收集娱乐数据。收集每个用户的流信息，例如当前观看者和追随者的数量，流类型等。从结果中，我们发现流媒体会话的频率，内容的类型和流的长度是确定在会话期间可以获得多少观众和订户的垃圾媒体。

Recent work has shown the benefits of synthetic data for use in computer vision, with applications ranging from autonomous driving to face landmark detection and reconstruction. There are a number of benefits of using synthetic data from privacy preservation and bias elimination to quality and feasibility of annotation. Generating human-centered synthetic data is a particular challenge in terms of realism and domain-gap, though recent work has shown that effective machine learning models can be trained using synthetic face data alone. We show that this can be extended to include the full body by building on the pipeline of Wood et al. to generate synthetic images of humans in their entirety, with ground-truth annotations for computer vision applications. In this report we describe how we construct a parametric model of the face and body, including articulated hands; our rendering pipeline to generate realistic images of humans based on this body model; an approach for training DNNs to regress a dense set of landmarks covering the entire body; and a method for fitting our body model to dense landmarks predicted from multiple views.

Differentiable Architecture Search (DARTS) has attracted considerable attention as a gradient-based Neural Architecture Search (NAS) method. Since the introduction of DARTS, there has been little work done on adapting the action space based on state-of-art architecture design principles for CNNs. In this work, we aim to address this gap by incrementally augmenting the DARTS search space with micro-design changes inspired by ConvNeXt and studying the trade-off between accuracy, evaluation layer count, and computational cost. To this end, we introduce the Pseudo-Inverted Bottleneck conv block intending to reduce the computational footprint of the inverted bottleneck block proposed in ConvNeXt. Our proposed architecture is much less sensitive to evaluation layer count and outperforms a DARTS network with similar size significantly, at layer counts as small as 2. Furthermore, with less layers, not only does it achieve higher accuracy with lower GMACs and parameter count, GradCAM comparisons show that our network is able to better detect distinctive features of target objects compared to DARTS.

Meta Learning automates the search for learning algorithms. At the same time, it creates a dependency on human engineering on the meta-level, where meta learning algorithms need to be designed. In this paper, we investigate self-referential meta learning systems that modify themselves without the need for explicit meta optimization. We discuss the relationship of such systems to in-context and memory-based meta learning and show that self-referential neural networks require functionality to be reused in the form of parameter sharing. Finally, we propose fitness monotonic execution (FME), a simple approach to avoid explicit meta optimization. A neural network self-modifies to solve bandit and classic control tasks, improves its self-modifications, and learns how to learn, purely by assigning more computational resources to better performing solutions.

There are two important things in science: (A) Finding answers to given questions, and (B) Coming up with good questions. Our artificial scientists not only learn to answer given questions, but also continually invent new questions, by proposing hypotheses to be verified or falsified through potentially complex and time-consuming experiments, including thought experiments akin to those of mathematicians. While an artificial scientist expands its knowledge, it remains biased towards the simplest, least costly experiments that still have surprising outcomes, until they become boring. We present an empirical analysis of the automatic generation of interesting experiments. In the first setting, we investigate self-invented experiments in a reinforcement-providing environment and show that they lead to effective exploration. In the second setting, pure thought experiments are implemented as the weights of recurrent neural networks generated by a neural experiment generator. Initially interesting thought experiments may become boring over time.

Recent advances in language modeling have enabled new conversational systems. In particular, it is often desirable for people to make choices among specified options when using such systems. We address the problem of reference resolution, when people use natural expressions to choose between real world entities. For example, given the choice `Should we make a Simnel cake or a Pandan cake?' a natural response from a non-expert may be indirect: `let's make the green one'. Reference resolution has been little studied with natural expressions, thus robustly understanding such language has large potential for improving naturalness in dialog, recommendation, and search systems. We create AltEntities (Alternative Entities), a new public dataset of entity pairs and utterances, and develop models for the disambiguation problem. Consisting of 42K indirect referring expressions across three domains, it enables for the first time the study of how large language models can be adapted to this task. We find they achieve 82%-87% accuracy in realistic settings, which while reasonable also invites further advances.

A typical product or place often has hundreds of reviews, and summarization of these texts is an important and challenging problem. Recent progress on abstractive summarization in domains such as news has been driven by supervised systems trained on hundreds of thousands of news articles paired with human-written summaries. However for opinion texts, such large scale datasets are rarely available. Unsupervised methods, self-training, and few-shot learning approaches bridge that gap. In this work, we present a novel self-training approach, OpineSum, for abstractive opinion summarization. The summaries in this approach are built using a novel application of textual entailment and capture the consensus of opinions across the various reviews for an item. This method can be used to obtain silver-standard summaries on a large scale and train both unsupervised and few-shot abstractive summarization systems. OpineSum achieves state-of-the-art performance in both settings.

We consider the problem of automatically generating stories in multiple languages. Compared to prior work in monolingual story generation, crosslingual story generation allows for more universal research on story planning. We propose to use Prompting Large Language Models with Plans to study which plan is optimal for story generation. We consider 4 types of plans and systematically analyse how the outputs differ for different planning strategies. The study demonstrates that formulating the plans as question-answer pairs leads to more coherent generated stories while the plan gives more control to the story creators.

Modern machine learning requires system designers to specify aspects of the learning pipeline, such as losses, architectures, and optimizers. Meta-learning, or learning-to-learn, instead aims to learn those aspects, and promises to unlock greater capabilities with less manual effort. One particularly ambitious goal of meta-learning is to train general-purpose in-context learning algorithms from scratch, using only black-box models with minimal inductive bias. Such a model takes in training data, and produces test-set predictions across a wide range of problems, without any explicit definition of an inference model, training loss, or optimization algorithm. In this paper we show that Transformers and other black-box models can be meta-trained to act as general-purpose in-context learners. We characterize phase transitions between algorithms that generalize, algorithms that memorize, and algorithms that fail to meta-train at all, induced by changes in model size, number of tasks, and meta-optimization. We further show that the capabilities of meta-trained algorithms are bottlenecked by the accessible state size (memory) determining the next prediction, unlike standard models which are thought to be bottlenecked by parameter count. Finally, we propose practical interventions such as biasing the training distribution that improve the meta-training and meta-generalization of general-purpose learning algorithms.