Currently, Artificial Intelligence (AI) gains great advances. However, current focus is functional AI, which provides some specific functions such as face recognition, the game of go and question-answer. Different from functional AI, conscious AI [6] aims to build AI systems with consciousness. Conscious AI will not only help to build better AI systems by solving the problem of data-driven approaches but also create the opportunity to study neuroscience and behavior science by connecting behavior with conscious activities. With its wide applications and great interests, many researchers devote to the model of consciousness.

Cooperation and collaboration robots, co-robots or cobots for short, are an integral part of factories. For example, they work closely with the fitters in the automotive sector, and everyone does what they do best. However, the novel robots are not only relevant in production and logistics, but also in the service sector, especially where proximity between them and the users is desired or unavoidable. For decades, individual solutions of a very different kind have been developed in care. Now experts are increasingly relying on co-robots and teaching them the special tasks that are involved in care or therapy. This article presents the advantages, but also the disadvantages of co-robots in care and support, and provides information with regard to human-robot interaction and communication. The article is based on a model that has already been tested in various nursing and retirement homes, namely Lio from F&P Robotics, and uses results from accompanying studies. The authors can show that co-robots are ideal for care and support in many ways. Of course, it is also important to consider a few points in order to guarantee functionality and acceptance.

Edge computation offloading allows mobile end devices to put execution of compute-intensive task on the edge servers. End devices can decide whether offload the tasks to edge servers, cloud servers or execute locally according to current network condition and devices' profile in an online manner. In this article, we propose an edge computation offloading framework based on Deep Imitation Learning (DIL) and Knowledge Distillation (KD), which assists end devices to quickly make fine-grained decisions to optimize the delay of computation tasks online. We formalize computation offloading problem into a multi-label classification problem. Training samples for our DIL model are generated in an offline manner. After model is trained, we leverage knowledge distillation to obtain a lightweight DIL model, by which we further reduce the model's inference delay. Numerical experiment shows that the offloading decisions made by our model outperforms those made by other related policies in latency metric. Also, our model has the shortest inference delay among all policies.

Deep Neural Networks are successful but highly computationally expensive learning systems. One of the main sources of time and energy drains is the well known backpropagation (backprop) algorithm, which roughly accounts for 2/3 of the computational complexity of training. In this work we propose a method for reducing the computational cost of backprop, which we named dithered backprop. It consists in applying a stochastic quantization scheme to intermediate results of the method. The particular quantisation scheme, called non-subtractive dither (NSD), induces sparsity which can be exploited by computing efficient sparse matrix multiplications. Experiments on popular image classification tasks show that it induces 92% sparsity on average across a wide set of models at no or negligible accuracy drop in comparison to state-of-the-art approaches, thus significantly reducing the computational complexity of the backward pass. Moreover, we show that our method is fully compatible to state-of-the-art training methods that reduce the bit-precision of training down to 8-bits, as such being able to further reduce the computational requirements. Finally we discuss and show potential benefits of applying dithered backprop in a distributed training setting, where both communication as well as compute efficiency may increase simultaneously with the number of participant nodes.

We undertake a precise study of the asymptotic and non-asymptotic properties of stochastic approximation procedures with Polyak-Ruppert averaging for solving a linear system $\bar{A} \theta = \bar{b}$. When the matrix $\bar{A}$ is Hurwitz, we prove a central limit theorem (CLT) for the averaged iterates with fixed step size and number of iterations going to infinity. The CLT characterizes the exact asymptotic covariance matrix, which is the sum of the classical Polyak-Ruppert covariance and a correction term that scales with the step size. Under assumptions on the tail of the noise distribution, we prove a non-asymptotic concentration inequality whose main term matches the covariance in CLT in any direction, up to universal constants. When the matrix $\bar{A}$ is not Hurwitz but only has non-negative real parts in its eigenvalues, we prove that the averaged LSA procedure actually achieves an $O(1/T)$ rate in mean-squared error. Our results provide a more refined understanding of linear stochastic approximation in both the asymptotic and non-asymptotic settings. We also show various applications of the main results, including the study of momentum-based stochastic gradient methods as well as temporal difference algorithms in reinforcement learning.

Classification is a fundamental problem in statistics and machine learning that arises in many scientific and engineering problems. Scientific applications include identifying plant and animal species from body measurements, determining cancer types based on gene expression, and satellite image processing (Fisher, 1936, 1938; Khan et al., 2001; Lee et al., 2004); in modern engineering contexts, credit card fraud detection, handwritten digit recognition, word sense disambiguation, and object detection in images are all examples of classification tasks. These applications have brought two new challenges: multiclass classification with a potentially large number of classes and imbalanced data. For example, in online retailing, websites have hundreds of thousands or millions of products, and they may like to categorize these products within a preexisting taxonomy based on product descriptions (Lin et al., 2018). While the number of classes alone makes the problem difficult, an added difficulty with text data is that it is usually highly imbalanced, meaning that a few classes may constitute a large fraction of the data while many classes have only a few examples. In fact, Feldman (2019) notes that if the data follows the classical Zipf distribution for text data (Zipf, 1936), i.e., the class probabilities satisfy a power-law distribution, then up to 35% of seen examples may appear only once in the training data. Additionally, natural image data also seems to have the problems of many classes and imbalanced data (Salakhutdinov et al., 2011; Zhu et al., 2014). Focusing on the problem of imbalanced data, researchers have found that a few heuristics help "do better," and the most principled and studied of these is weighting. There are a number of forms of weighting; we consider the most basic in which we incur a loss of weight for misclassifying an example of class and refer to this method as class-weighting.

Most recently, with the proliferation of IoT devices, computational nodes in manufacturing systems IIoT(Industrial-Internet-of-things) and the lunch of 5G networks, there will be millions of connected devices generating a massive amount of data. In such an environment, the controlling systems need to be intelligent enough to deal with a vast amount of data to detect defects in a real-time process. Driven by such a need, artificial intelligence models such as deep learning have to be deployed into IIoT systems. However, learning and using deep learning models are computationally expensive, so an IoT device with limited computational power could not run such models. To tackle this issue, edge intelligence had emerged as a new paradigm towards running Artificial Intelligence models on edge devices. Although a considerable amount of studies have been proposed in this area, the research is still in the early stages. In this paper, we propose a novel edge-based multi-phase pruning pipelines to ensemble learning on IIoT devices. In the first phase, we generate a diverse ensemble of pruned models, then we apply integer quantisation, next we prune the generated ensemble using a clustering-based technique. Finally, we choose the best representative from each generated cluster to be deployed to a distributed IoT environment. On CIFAR-100 and CIFAR-10, our proposed approach was able to outperform the predictability levels of a baseline model (up to 7%), more importantly, the generated learners have small sizes (up to 90% reduction in the model size) that minimise the required computational capabilities to make an inference on the resource-constraint devices.

Link prediction, or the inference of future or missing connections between entities, is a well-studied problem in network analysis. A multitude of heuristics exist for link prediction in ordinary networks with a single type of connection. However, link prediction in multiplex networks, or networks with multiple types of connections, is not a well understood problem. We propose a novel general framework and three families of heuristics for multiplex network link prediction that are simple, interpretable, and take advantage of the rich connection type correlation structure that exists in many real world networks. We further derive a theoretical threshold for determining when to use a different connection type based on the number of links that overlap with an Erdos-Renyi random graph. Through experiments with simulated and real world scientific collaboration, transportation and global trade networks, we demonstrate that the proposed heuristics show increased performance with the richness of connection type correlation structure and significantly outperform their baseline heuristics for ordinary networks with a single connection type.

Convolutional Neural Networks (CNNs) work very well for supervised learning problems when the training dataset is representative of the variations expected to be encountered at test time. In medical image segmentation, this premise is violated when there is a mismatch between training and test images in terms of their acquisition details, such as the scanner model or the protocol. Remarkable performance degradation of CNNs in this scenario is well documented in the literature. To address this problem, we design the segmentation CNN as a concatenation of two sub-networks: a relatively shallow image normalization CNN, followed by a deep CNN that segments the normalized image. We train both these sub-networks using a training dataset, consisting of annotated images from a particular scanner and protocol setting. Now, at test time, we adapt the image normalization sub-network for each test image, guided by an implicit prior on the predicted segmentation labels. We employ an independently trained denoising autoencoder (DAE) in order to model such an implicit prior on plausible anatomical segmentation labels. We validate the proposed idea on multi-center Magnetic Resonance imaging datasets of three anatomies: brain, heart and prostate. The proposed test-time adaptation consistently provides performance improvement, demonstrating the promise and generality of the approach. Being agnostic to the architecture of the deep CNN, the second sub-network, the proposed design can be utilized with any segmentation network to increase robustness to variations in imaging scanners and protocols.

Electronic Health Records (EHRs) provide vital contextual information to radiologists and other physicians when making a diagnosis. Unfortunately, because a given patient's record may contain hundreds of notes and reports, identifying relevant information within these in the short time typically allotted to a case is very difficult. We propose and evaluate models that extract relevant text snippets from patient records to provide a rough case summary intended to aid physicians considering one or more diagnoses. This is hard because direct supervision (i.e., physician annotations of snippets relevant to specific diagnoses in medical records) is prohibitively expensive to collect at scale. We propose a distantly supervised strategy in which we use groups of International Classification of Diseases (ICD) codes observed in 'future' records as noisy proxies for 'downstream' diagnoses. Using this we train a transformer-based neural model to perform extractive summarization conditioned on potential diagnoses. This model defines an attention mechanism that is conditioned on potential diagnoses (queries) provided by the diagnosing physician. We train (via distant supervision) and evaluate variants of this model on EHR data from a local hospital and MIMIC-III (the latter to facilitate reproducibility). Evaluations performed by radiologists demonstrate that these distantly supervised models yield better extractive summaries than do unsupervised approaches. Such models may aid diagnosis by identifying sentences in past patient reports that are clinically relevant to a potential diagnoses.