Many environments currently employ machine learning models for data processing and analytics that were built using a limited number of training data points. Once deployed, the models are exposed to significant amounts of previously-unseen data, not all of which is representative of the original, limited training data. However, updating these deployed models can be difficult due to logistical, bandwidth, time, hardware, and/or data sensitivity constraints. We propose a framework, Self-Updating Models with Error Remediation (SUMER), in which a deployed model updates itself as new data becomes available. SUMER uses techniques from semi-supervised learning and noise remediation to iteratively retrain a deployed model using intelligently-chosen predictions from the model as the labels for new training iterations. A key component of SUMER is the notion of error remediation as self-labeled data can be susceptible to the propagation of errors. We investigate the use of SUMER across various data sets and iterations. We find that self-updating models (SUMs) generally perform better than models that do not attempt to self-update when presented with additional previously-unseen data. This performance gap is accentuated in cases where there is only limited amounts of initial training data. We also find that the performance of SUMER is generally better than the performance of SUMs, demonstrating a benefit in applying error remediation. Consequently, SUMER can autonomously enhance the operational capabilities of existing data processing systems by intelligently updating models in dynamic environments.

Adversarial examples are data points misclassified by neural networks. Originally, adversarial examples were limited to adding small perturbations to a given image. Recent work introduced the generalized concept of unrestricted adversarial examples, without limits on the added perturbations. In this paper, we introduce a new category of attacks that create unrestricted adversarial examples for object detection. Our key idea is to generate adversarial objects that are unrelated to the classes identified by the target object detector. Different from previous attacks, we use off-the-shelf Generative Adversarial Networks (GAN), without requiring any further training or modification. Our method consists of searching over the latent normal space of the GAN for adversarial objects that are wrongly identified by the target object detector. We evaluate this method on the commonly used Faster R-CNN ResNet-101, Inception v2 and SSD Mobilenet v1 object detectors using logo generative iWGAN-LC and SNGAN trained on CIFAR-10. The empirical results show that the generated adversarial objects are indistinguishable from non-adversarial objects generated by the GANs, transferable between the object detectors and robust in the physical world. This is the first work to study unrestricted false positive adversarial examples for object detection.

We introduce a graph clustering algorithm that generalizes $k$-means to graphs. Our method utilizes PageRank measures on graphs to quickly and robustly compute centrality of nodes in a given graph. Furthermore, we show how our method can be generalized to metric spaces and apply it to other domains such as point clouds and triangulated meshes.

In recent years, few-shot learning problems have received a lot of attention. While methods in most previous works were trained and tested on datasets in one single domain, cross-domain few-shot learning is a brand-new branch of few-shot learning problems, where models handle datasets in different domains between training and testing phases. In this paper, to solve the problem that the model is pre-trained (meta-trained) on a single dataset while fine-tuned on datasets in four different domains, including common objects, satellite images, and medical images, we propose a novel large margin fine-tuning method (LMM-PQS), which generates pseudo query images from support images and fine-tunes the feature extraction modules with a large margin mechanism inspired by methods in face recognition. According to the experiment results, LMM-PQS surpasses the baseline models by a significant margin and demonstrates that our approach is robust and can easily adapt pre-trained models to new domains with few data.

Their importance has been highlighted in recent times, when ICUs around the world have been overrun by the COVID-19 pandemic [1, 2]. It is in times like these when research into ways to adequately manage scarce critical care resources must be even more vigorously pursued, in order to offer additional tools that support medical decisions and allow for the effective benchmark of clinical practice. The issue of mortality prediction in the ICU has been approached from a statistical standpoint by means of risk prediction models like APACHE, SAPS, MODS, among others [3]. These models use a set of physiological predictors, demographic factors, and the occurrence of certain chronic conditions, to estimate a score that serves as a proxy for the likelihood of death of ICU patients. Because of the relatively straightforward way of interpreting results, simple statistical approaches such as logistic regression are the go-to modeling techniques used to estimate mortality probability and the importance of the predictors involved. On the other hand, the simplicity of the models also mean that their limited expressiveness may not accurately represent the possibly nonlinear dynamics of mortality prediction. Given this, high-capacity machine learning models might be useful to increase predictive performance.

The RNN transducer is a promising end-to-end model candidate. We compare the original training criterion with the full marginalization over all alignments, to the commonly used maximum approximation, which simplifies, improves and speeds up our training. We also generalize from the original neural network model and study more powerful models, made possible due to the maximum approximation. We further generalize the output label topology to cover RNN-T, RNA and CTC. We perform several studies among all these aspects, including a study on the effect of external alignments. We find that the transducer model generalizes much better on longer sequences than the attention model. Our final transducer model outperforms our attention model on Switchboard 300h by over 6% relative WER.

Using privileged information during training can improve the sample efficiency and performance of machine learning systems. This paradigm has been applied to reinforcement learning (RL), primarily in the form of distillation or auxiliary tasks, and less commonly in the form of augmenting the inputs of agents. In this work, we investigate Privileged Information Dropout (PI-Dropout) for achieving the latter which can be applied equally to value-based and policy-based RL algorithms. Within a simple partially-observed environment, we demonstrate that PI-Dropout outperforms alternatives for leveraging privileged information, including distillation and auxiliary tasks, and can successfully utilise different types of privileged information. Finally, we analyse its effect on the learned representations.

Spatio-temporal sequence forecasting is one of the fundamental tasks in spatio-temporal data mining. It facilitates many real world applications such as precipitation nowcasting, citywide crowd flow prediction and air pollution forecasting. Recently, a few Seq2Seq based approaches have been proposed, but one of the drawbacks of Seq2Seq models is that, small errors can accumulate quickly along the generated sequence at the inference stage due to the different distributions of training and inference phase. That is because Seq2Seq models minimise single step errors only during training, however the entire sequence has to be generated during the inference phase which generates a discrepancy between training and inference. In this work, we propose a novel curriculum learning based strategy named Temporal Progressive Growing Sampling to effectively bridge the gap between training and inference for spatio-temporal sequence forecasting, by transforming the training process from a fully-supervised manner which utilises all available previous ground-truth values to a less-supervised manner which replaces some of the ground-truth context with generated predictions. To do that we sample the target sequence from midway outputs from intermediate models trained with bigger timescales through a carefully designed decaying strategy. Experimental results demonstrate that our proposed method better models long term dependencies and outperforms baseline approaches on two competitive datasets.

In this paper, we investigate the combination of synthesis techniques and learning techniques to obtain safe and near optimal schedulers for a preemptible task scheduling problem. We study both model-based learning techniques with PAC guarantees and model-free learning techniques based on shielded deep Q-learning. The new learning algorithms have been implemented to conduct experimental evaluations.

As AI is deployed increasingly broadly, AI researchers are confronted with the moral implications of their work. The pursuit of simple objectives, such as minimizing error rates, maximizing resource efficiency, or decreasing response times, often results in systems that have unintended consequences when they confront the real world, such as discriminating against certain groups of people [34]. It would be helpful for AI researchers and practitioners to have a general set of principles with which to approach these problems [45, 41, 24, 16, 33]. One may ask why any moral decisions should be left to computers at all. There are multiple possible reasons. One is that the decision needs to be made so quickly that calling in a human for the decision is not feasible, as would be the case for a self-driving car having to make a split-second decision about whom to hit [13]. Another reason could be that each individual decision by itself is too insignificant to bother a human, even though all the decisions combined may be highly significant morally--for example, if we were to consider the moral impact of each advertisement shown online. A third reason is that the moral decision is hard to decouple from a computational problem that apparently exceeds human capabilities. This is the case in many machine learning applications (e.g., should this person be released on bail?