Most high-performance expert systems rely primarily on an ability to represent surface knowledge about associations between observable evidence or data, on the one hand, and hypotheses or classifications of interest, on the other. Although the present generation of practical systems shows that this architectural style can be pushed quite far, the limitations of current systems motivate a search for representations that would allow expert systems to move beyond the prevalent "symptom-disease" style. One approach that appears promising is to couple a rule-based or associational system module with some other computational model of the phenomenon or domain of interest. According to this approach, the domain knowledge captured in the second model would be selected to complement the associational knowledge represented in the first module. Simulation models have been especially attractive choices for the complementary representation because of the causal relations embedded in them (Brown & Burton, 1975; Cuena, 1983).
Facebook is cracking down on false anti-vaccine content on its platform following a spike in vaccine-preventable diseases around the world. Disinformation campaigns from the controversial anti-vax movement have plagued social media platforms in recent years, fuelled by the misguided belief in scientifically disproven claims that vaccinations are harmful and can cause autism. Facebook has been repeatedly accused of helping to spread those myths, as well as other disinformation. We'll tell you what's true. You can form your own view.
Google DeepMind has announced its second collaboration with the NHS, as part of which it will work with Moorfields Eye Hospital in east London to build a machine learning system which will eventually be able to recognise sight-threatening conditions from just a digital scan of the eye. The five-year research project will draw on one million anonymous eye scans which are held on Moorfields' patient database, reports Ars Technica, with the aim to speed up the complex and time-consuming process of analysing eye scans. From the report:The hope is that this will allow diagnoses of common causes of sight loss, like diabetic retinopathy and age-related macular degeneration, to be spotted more rapidly and hence be treated more effectively. For example, Google says that up to 98 percent of sight loss resulting from diabetes can be prevented by early detection and treatment. Two million people are already living with sight loss in the UK, of whom around 360,000 are registered as blind or partially-sighted.
Infectious diseases are studied to understand their spreading mechanisms, to evaluate control strategies and to predict the risk and course of future outbreaks. Because people only interact with a small number of individuals, and because the structure of these interactions matters for spreading processes, the pairwise relationships between individuals in a population can be usefully represented by a network. Although the underlying processes of transmission are different, the network approach can be used to study the spread of pathogens in a contact network or the spread of rumors in an online social network. We study simulated simple and complex epidemics on synthetic networks and on two empirical networks, a social / contact network in an Indian village and an online social network in the U.S. Our goal is to learn simultaneously about the spreading process parameters and the source node (first infected node) of the epidemic, given a fixed and known network structure, and observations about state of nodes at several points in time. Our inference scheme is based on approximate Bayesian computation (ABC), an inference technique for complex models with likelihood functions that are either expensive to evaluate or analytically intractable. ABC enables us to adopt a Bayesian approach to the problem despite the posterior distribution being very complex. Our method is agnostic about the topology of the network and the nature of the spreading process. It generally performs well and, somewhat counter-intuitively, the inference problem appears to be easier on more heterogeneous network topologies, which enhances its future applicability to real-world settings where few networks have homogeneous topologies.
Marcolino, Leandro Soriano (University of Southern California) | Lakshminarayanan, Aravind (Indian Institute of Technology, Madras) | Yadav, Amulya (University of Southern California) | Tambe, Milind (University of Southern California)
Influence Maximization is an active topic, but it was always assumed full knowledge of the social network graph. However, the graph may actually be unknown beforehand. For example, when selecting a subset of a homeless population to attend interventions concerning health, we deal with a network that is not fully known. Hence, we introduce the novel problem of simultaneously influencing and mapping (i.e., learning) the graph. We study a class of algorithms, where we show that: (i) traditional algorithms may have arbitrarily low performance; (ii) we can effectively influence and map when the independence of objectives hypothesis holds; (iii) when it does not hold, the upper bound for the influence loss converges to 0. We run extensive experiments over four real-life social networks, where we study two alternative models, and obtain significantly better results in both than traditional approaches.