Professor Hao Li used to think it could take two to three years for the perfection of deepfake videos to make copycats indistinguishable from reality. But now, the associate professor of computer science at the University of Southern California, says this technology could be perfected in as soon as six to 12 months. Deepfakes are realistic manipulated videos that can, for example, make it look a person said or did something they didn't. "The best possible algorithm will not be able to distinguish," he says of the difference between a perfect deepfake and real videos. Li says he's changed his mind because developments in computer graphics and artificial intelligence are accelerating the development of deepfake applications.

Some companies just don't mess around … They see the future and embrace the tools and resources to take them there. That's how the Storefriendly self-storage brand in Asia is doing it! The operator just released an innovative video that not only highlights its GObots unit-retrieval service but displays the power of artificial intelligence (AI). "Make Space for the Future" was developed by feeding 200 pieces of company-related information into an AI program and machine-learning system. The result is a flamboyant ad featuring Gary the GObot that illustrates the operator's services, technology features, customer appeal and more.

AI having applications in various sectors including agriculture has completely transformed the approaches of the agriculture market. AI in Agriculture helps the farmers in examining weather, soil, and field data to improve farming operations and crop productivity. AI in the agriculture market seems to be driven by the Internet of Things (IoT) due to its ability to revolutionize and transform current farming methods to a new level. Although, collecting accurate field data requires high initial investments which may hamper the growth of AI in the agriculture market. Some of the leading companies influencing the market are Ag Leader Technology, Trimble, Agribotix, Granular, SAP, Mavrx, PrecisionHawk, aWhere, IBM and Prospera Technologies.

With the rapid growth of knowledge, it shows a steady trend of knowledge fragmentization. Knowledge fragmentization manifests as that the knowledge related to a specific topic in a course is scattered in isolated and autonomous knowledge sources. We term the knowledge of a facet in a specific topic as a knowledge fragment. The problem of knowledge fragmentization brings two challenges: First, knowledge is scattered in various knowledge sources, which exerts users' considerable efforts to search for the knowledge of their interested topics, thereby leading to information overload. Second, learning dependencies which refer to the precedence relationships between topics in the learning process are concealed by the isolation and autonomy of knowledge sources, thus causing learning disorientation. To solve the knowledge fragmentization problem, we propose a novel knowledge organization model, knowledge forest, which consists of facet trees and learning dependencies. Facet trees can organize knowledge fragments with facet hyponymy to alleviate information overload. Learning dependencies can organize disordered topics to cope with learning disorientation. We conduct extensive experiments on three manually constructed datasets from the Data Structure, Data Mining, and Computer Network courses, and the experimental results show that knowledge forest can effectively organize knowledge fragments, and alleviate information overload and learning disorientation.

PERSONALIZA TION OF END-TO-END SPEECH RECOGNITION ON MOBILE DEVICES FOR NAMED ENTITIES Khe Chai Sim, Franc oise Beaufays, Arnaud Benard, Dhruv Guliani, Andreas Kabel, Nikhil Khare, T amar Lucassen, Petr Zadrazil, Harry Zhang, Leif Johnson, Giovanni Motta, Lillian Zhou Google, USA ABSTRACT We study the effectiveness of several techniques to personalize end-to-end speech models and improve the recognition of proper names relevant to the user. These techniques differ in the amounts of user effort required to provide supervision, and are evaluated on how they impact speech recognition performance. We propose using keyword-dependent precision and recall metrics to measure vocabulary acquisition performance. We evaluate the algorithms on a dataset that we designed to contain names of persons that are difficult to recognize. Therefore, the baseline recall rate for proper names in this dataset is very low: 2.4%. A data synthesis approach we developed brings it to 48.6%, with no need for speech input from the user. With speech input, if the user corrects only the names, the name recall rate improves to 64.4%. If the user corrects all the recognition errors, we achieve the best recall of 73.5%. To eliminate the need to upload user data and store personalized models on a server, we focus on performing the entire personalization workflow on a mobile device.

A two-layer neural network model that systematically includes correlations among input variables to arbitrary order and is designed to implement Bayes inference has been adapted to classify breast cancer tumors as malignant or benign, assigning a probability for either outcome. The inputs to the network represent measured characteristics of cell nuclei imaged in Fine Needle Aspiration biopsies. The present machine-learning approach to diagnosis (known as HOPP, for higher-order probabilistic perceptron) is tested on the much-studied, open-access Breast Cancer Wisconsin (Diagnosis) Data Set of Wolberg et al. This set lists, for each tumor, measured physical parameters of the cell nuclei of each sample. The HOPP model can identify the key factors -- input features and their combinations -- most relevant for reliable diagnosis. HOPP networks were trained on 90\% of the examples in the Wisconsin database, and tested on the remaining 10\%. Referred to ensembles of 300 networks, selected randomly for cross-validation, accuracy of classification for the test sets of up to 97\% was readily achieved, with standard deviation around 2\%, together with average Matthews correlation coefficients reaching 0.94 indicating excellent predictive performance. Demonstrably, the HOPP is capable of matching the predictive power attained by other advanced machine-learning algorithms applied to this much-studied database, over several decades. Analysis shows that in this special problem, which is almost linearly separable, the effects of irreducible correlations among the measured features of the Wisconsin database are of relatively minor importance, as the Naive Bayes approximation can itself yield predictive accuracy approaching 95\%. The advantages of the HOPP algorithm will be more clearly revealed in application to more challenging machine-learning problems.

A distinction has been drawn in fair machine learning research between'group' and'individual' fairness measures. Many tec hnical research papers assume that both are important, but conflict ing, and propose ways to minimise the tradeoffs between these mea - sures. This paper argues that this apparent conflict is based on a misconception. It draws on theoretical discussions from within the fair machine learning research, and from political and legal philosophy, to argue that individual and group fairness are not fun da-mentally in conflict. First, it outlines accounts of egalita rian fairness which encompass plausible motivations for both group a nd individual fairness, thereby suggesting that there need be no conflict in principle. Second, it considers the concept of individual justice, from legal philosophy and jurisprudence which seems similar but actually contradicts the notion of individual fairness as proposed in the fair machine learning literature. The conclusi on is that the apparent conflict between individual and group fair ness is more of an artefact of the blunt application of fairness measures, rather than a matter of conflicting principles. In practice, this conflict may be resolved by a nuanced consideration of the sources of'unfairness' in a particular deployment context, and the ca refully justified application of measures to mitigate it.

Sleep apnea is a common respiratory disorder characterized by breathing pauses during the night. Consequences of untreated sleep apnea can be severe. Still, many people remain undiagnosed due to shortages of hospital beds and trained sleep technicians. To assist in the diagnosis process, automated detection methods are being developed. Recent works have demonstrated that deep learning models can extract useful information from raw respiratory data and that such models can be used as a robust sleep apnea detector. However, trained sleep technicians take into account multiple sensor signals when annotating sleep recordings instead of relying on a single respiratory estimate. To improve the predictive performance and reliability of the models, early and late sensor fusion methods are explored in this work. In addition, a novel late sensor fusion method is proposed which uses backward shortcut connections to improve the learning of the first stages of the models. The performance of these fusion methods is analyzed using CNN as well as LSTM deep learning base-models. The results demonstrate a significant and consistent improvement in predictive performance over the single sensor methods and over the other explored sensor fusion methods, by using the proposed sensor fusion method with backward shortcut connections.

We propose a new contextual-compositional neural network layer that handles out-of-vocabulary (OOV) words in natural language processing (NLP) tagging tasks. This layer consists of a model that attends to both the character sequence and the context in which the OOV words appear. We show that our model learns to generate task-specific \textit{and} sentence-dependent OOV word representations without the need for pre-training on an embedding table, unlike previous attempts. We insert our layer in the state-of-the-art tagging model of \citet{plank2016multilingual} and thoroughly evaluate its contribution on 23 different languages on the task of jointly tagging part-of-speech and morphosyntactic attributes. Our OOV handling method successfully improves performances of this model on every language but one to achieve a new state-of-the-art on the Universal Dependencies Dataset 1.4.

Multi-agent reinforcement learning has been successfully applied to a number of challenging problems. Despite these empirical successes, theoretical understanding of different algorithms is lacking, primarily due to the curse of dimensionality caused by the exponential growth of the state-action space with the number of agents. We study a fundamental problem of multi-agent linear quadratic regulator in a setting where the agents are partially exchangeable. In this setting, we develop a hierarchical actor-critic algorithm, whose computational complexity is independent of the total number of agents, and prove its global linear convergence to the optimal policy. As linear quadratic regulators are often used to approximate general dynamic systems, this paper provided an important step towards better understanding of general hierarchical mean-field multi-agent reinforcement learning.