Artificial intelligence (AI), Machine learning, NLP, Robotics, and Automation are increasingly prevalent in all aspects and are being applied to healthcare as well. These technologies have the potential to transform all aspects of health care from patient care to the development and production of new experimental drugs that can have a faster roll-out date than traditional methods. There are numerous research studies suggesting that AI can outperform humans at key healthcare tasks, such as diagnosing ailments. Here is a great example, AI'outperforms' doctors diagnosing breast cancer¹. Artificial intelligence is a collection of technologies that come together form artificial intelligence. Tech firms and startups are also working assiduously on the same issues.

Imtiaz Adam, Twitter @Deeplearn007 Updated a few sections in Sep 2020 Artificial Intelligence (AI) is increasingly affecting the world around us. It is increasingly making an impact in retail, financial services, along with other sectors of the economy.

A way of monitoring household appliances by using machine learning to analyse vibrations on a wall or ceiling has been developed by researchers in the US. Their system could be used to create centralized smart home systems without the need for individual sensors in each object. What is more, the technology could help track energy use, identify electrical faults and even remind people to empty the dishwasher. "Recognizing home activities can help computers better understand human behaviours and needs, with the hope of developing a better human-machine interface," says team member and information scientist Cheng Zhang of Cornell University. The system, dubbed VibroSense, comprises two core parts: a laser Doppler vibrometer and a deep learning model, which is a type of machine learning system.

LSTMs are one of the most important breakthroughs in machine learning; Giving machine learning algorithms the ability to recall past information, allows for the realization of temporal patterns. How better to understand a concept, than to create it from scratch? LSTM stands for Long short-term memory, denoting its ability to use past information to make predictions. The mechanism behind the LSTM is quite simple. Instead of a single feedforward process for the data to be propagated through, LSTMs have different sources of processed information, from different timesteps as inputs for the networks, therefore being able to access time-related patterns within the data.

Deep learning approaches to anomaly detection have recently improved the state of the art in detection performance on complex datasets such as large collections of images or text. These results have sparked a renewed interest in the anomaly detection problem and led to the introduction of a great variety of new methods. With the emergence of numerous such methods, including approaches based on generative models, one-class classification, and reconstruction, there is a growing need to bring methods of this field into a systematic and unified perspective. In this review we aim to identify the common underlying principles as well as the assumptions that are often made implicitly by various methods. In particular, we draw connections between classic 'shallow' and novel deep approaches and show how this relation might cross-fertilize or extend both directions. We further provide an empirical assessment of major existing methods that is enriched by the use of recent explainability techniques, and present specific worked-through examples together with practical advice. Finally, we outline critical open challenges and identify specific paths for future research in anomaly detection.

Traditional linear subspace reduced order models (LS-ROMs) are able to accelerate physical simulations, in which the intrinsic solution space falls into a subspace with a small dimension, i.e., the solution space has a small Kolmogorov n-width. However, for physical phenomena not of this type, e.g., any advection-dominated flow phenomena, such as in traffic flow, atmospheric flows, and air flow over vehicles, a low-dimensional linear subspace poorly approximates the solution. To address cases such as these, we have developed a fast and accurate physics-informed neural network ROM, namely nonlinear manifold ROM (NM-ROM), which can better approximate high-fidelity model solutions with a smaller latent space dimension than the LS-ROMs. Our method takes advantage of the existing numerical methods that are used to solve the corresponding full order models. The efficiency is achieved by developing a hyper-reduction technique in the context of the NM-ROM. Numerical results show that neural networks can learn a more efficient latent space representation on advection-dominated data from 1D and 2D Burgers' equations. A speedup of up to 2.6 for 1D Burgers' and a speedup of 11.7 for 2D Burgers' equations are achieved with an appropriate treatment of the nonlinear terms through a hyper-reduction technique. Finally, a posteriori error bounds for the NM-ROMs are derived that take account of the hyper-reduced operators.

In recent years there has been a cascade of research in attempting to make AI systems more interpretable by providing explanations; so-called Explainable AI (XAI). Most of this research has dealt with the challenges that arise in explaining black-box deep learning systems in classification and regression tasks, with a focus on tabular and image data; for example, there is a rich seam of work on post-hoc counterfactual explanations for a variety of black-box classifiers (e.g., when a user is refused a loan, the counterfactual explanation tells the user about the conditions under which they would get the loan). However, less attention has been paid to the parallel interpretability challenges arising in AI systems dealing with time series data. This paper advances a novel technique, called Native-Guide, for the generation of proximal and plausible counterfactual explanations for instance-based time series classification tasks (e.g., where users are provided with alternative time series to explain how a classification might change). The Native-Guide method retrieves and uses native in-sample counterfactuals that already exist in the training data as "guides" for perturbation in time series counterfactual generation. This method can be coupled with both Euclidean and Dynamic Time Warping (DTW) distance measures. After illustrating the technique on a case study involving a climate classification task, we reported on a comprehensive series of experiments on both real-world and synthetic data sets from the UCR archive. These experiments provide computational evidence of the quality of the counterfactual explanations generated.

Learning general-purpose representations from multisensor data produced by the omnipresent sensing systems (or IoT in general) has numerous applications in diverse use areas. Existing purely supervised end-to-end deep learning techniques depend on the availability of a massive amount of well-curated data, acquiring which is notoriously difficult but required to achieve a sufficient level of generalization on a task of interest. In this work, we leverage the self-supervised learning paradigm towards realizing the vision of continual learning from unlabeled inputs. We present a generalized framework named Sense and Learn for representation or feature learning from raw sensory data. It consists of eight auxiliary tasks that can learn high-level and broadly useful features entirely from unannotated data without any human involvement in the tedious labeling process. We demonstrate the efficacy of our approach on several publicly available datasets from different domains and in various settings, including linear separability, semi-supervised or few shot learning, and transfer learning. Our methodology achieves results that are competitive with the supervised approaches and close the gap through fine-tuning a network while learning the downstream tasks in most cases. In particular, we show that the self-supervised network can be utilized as initialization to significantly boost the performance in a low-data regime with as few as 5 labeled instances per class, which is of high practical importance to real-world problems. Likewise, the learned representations with self-supervision are found to be highly transferable between related datasets, even when few labeled instances are available from the target domains. The self-learning nature of our methodology opens up exciting possibilities for on-device continual learning.

Task-oriented dialogue systems are either modularized with separate dialogue state tracking (DST) and management steps or end-to-end trainable. In either case, the knowledge base (KB) plays an essential role in fulfilling user requests. Modularized systems rely on DST to interact with the KB, which is expensive in terms of annotation and inference time. End-to-end systems use the KB directly as input, but they cannot scale when the KB is larger than a few hundred entries. In this paper, we propose a method to embed the KB, of any size, directly into the model parameters. The resulting model does not require any DST or template responses, nor the KB as input, and it can dynamically update its KB via fine-tuning. We evaluate our solution in five task-oriented dialogue datasets with small, medium, and large KB size. Our experiments show that end-to-end models can effectively embed knowledge bases in their parameters and achieve competitive performance in all evaluated datasets.

The nodes of a graph existing in a specific cluster are more likely to connect to each other than with other nodes in the graph. Then revealing some information about the nodes, the structure of the graph (the graph edges) provides this opportunity to know more information about the other nodes. From this perspective, this paper revisits the node classification task in a semi-supervised scenario by graph convolutional neural network. The goal is to benefit from the flow of information that circulates around the revealed node labels. For this aim, this paper provides a new graph convolutional neural network architecture. This architecture benefits efficiently from the revealed training nodes, the node features, and the graph structure. On the other hand, in many applications, non-graph observations (side information) exist beside a given graph realization. The non-graph observations are usually independent of the graph structure. This paper shows that the proposed architecture is also powerful in combining a graph realization and independent non-graph observations. For both cases, the experiments on the synthetic and real-world datasets demonstrate that our proposed architecture achieves a higher prediction accuracy in comparison to the existing state-of-the-art methods for the node classification task.