The annual CES technology conference closed out at more than 170 mph on Friday with the Indy Autonomous Challenge. The autonomous race car competition came to the Las Vegas Motor Speedway with five teams from seven universities racing self-driving cars for the first place title and $150,000. Team PoliMOVE from Politecnico di Milano in Italy and the University of Alabama beat out Team TUM Autonomous Motorsport from the Technische Universität München in Germany in the final head-to-head race. The race was close with Team TUM spinning out at the end. But TUM couldn't catch up from behind nor keep up with PoliMOVE's record speed of 173 mph.

Large space structures, such as telescopes and spacecraft, should ideally be assembled directly in space, as they are difficult or impossible to launch from Earth as a single piece. In several cases, however, assembling these technologies manually in space is either highly expensive or unfeasible. In recent years, roboticists have thus been trying to develop systems that could be used to automatically assemble structures in space. To simplify this assembly process, space structures could have a modular design, which essentially means that they are comprised of different building blocks or modules that can be shifted to create different shapes or forms. Researchers at the German Aerospace Center (DLR) and Technische Universität München (TUM) have recently developed an autonomous planner that could be used to assemble reconfigurable structures directly in space.

No longer content to simply provide a platform for keeping up with long-lost cousins and spreading conspiracy theories, Facebook has branched out into developing artificial intelligence to help treat complex diseases. The social media giant's AI research department and the Helmholtz Zentrum München, a research center in Germany focused on environmental health, unveiled an open-source AI model designed to determine the viability of repurposing existing drugs into new pharmaceutical cocktails. Researchers and biologists now have free access to the Compositional Perturbation Autoencoder, or CPA, which evaluates the effects of drug combinations in varying dosages--a complicated task, as the number of possibilities can accelerate exponentially into the billions as more medicines are thrown into the mix. The model predicts not only how the drugs interact with one another, but also how they might work together to attack specific cell types and interrupt diseases. The researchers trained the machine learning model on single-cell RNA sequencing data, to help it gauge the effects of drug cocktails on individual cells without requiring drug- or cell-specific programming.

The past 10 years have seen enormous breakthroughs in machine learning, resulting in game-changing applications in computer vision and language processing. The field of intelligent robotics, which aspires to construct robots that can perform a broad range of tasks in a variety of environments with general human-level intelligence, has not yet been revolutionized by these breakthroughs. A critical difficulty is that the necessary learning depends on data that can only come from acting in a variety of real-world environments. Such data are costly to acquire because there is enormous variability in the situations a general-purpose robot must cope with. It will take a combination of new algorithmic techniques, inspiration from natural systems, and multiple levels of machine learning to revolutionize robotics with general-purpose intelligence. Most of the successes in deep-learning applications have been in supervised machine learning, a setting in which the learning algorithm is given paired examples of an input and a desired output and it learns to associate them. For robots that execute sequences of actions in the world, a more appropriate framing of the learning problem is reinforcement learning (RL) ([ 1 ][1]), in which an “agent” learns to select actions to take within its environment in response to a “reward” signal that tells it when it is behaving well or poorly. One essential difference between supervised learning and RL is that the agent's actions have substantial influence over the data it acquires; the agent's ability to control its own exploration is critical to its overall success. The original inspirations for RL were models of animal behavior learning through reward and punishment. If RL is to be applied to interesting real-world problems, it must be extended to handle very large spaces of inputs and actions and to work when the rewards may arrive long after the critical action was chosen. New “deep” RL (DRL) methods, which use complex neural networks with many layers, have met these challenges and have resulted in stunning performance, including solving the games of chess and Go ([ 2 ][2]) and physically solving Rubik's Cube with a robot hand ([ 3 ][3]). They have also seen useful applications, including energy efficiency improvement in computer installations. On the basis of these successes, it is tempting to imagine that RL might completely replace traditional methods of engineering for robots and other systems with complex behavior in the physical world. There are technical reasons to resist this temptation. Consider a robot that is designed to help in an older person's household. The robot would have to be shipped with a considerable amount of prior knowledge and ability, but it would also need to be able to learn on the job. This learning would have to be sample efficient (requiring relatively few training examples), generalizable [applicable to many situations other than the one(s) it learned], compositional (represented in a form that allows it to be combined with previous knowledge), and incremental (capable of adding new knowledge and abilities over time). Most current DRL approaches do not have these properties: They can learn surprising new abilities, but generally they require a lot of experience, do not generalize well, and are monolithic during training and execution (i.e., neither incremental nor compositional). How can sample efficiency, generalizability, compositionality, and incrementality be enabled in an intelligent system? Modern neural networks have been shown to be effective at interpolating: Given a large number of parameters, they are able to remember the training data and make reliable predictions on similar examples ([ 4 ][4]). To obtain generalization, it is necessary to provide “inductive bias,” in the form of built-in knowledge or structure, to the learning algorithm. As an example, consider an autonomous car with an inductive bias that its braking strategy need only depend on cars within a bounded distance of it. Such a car's intelligence could learn from relatively few examples because of the limited set of possible strategies that would fit well with the data it has observed. Inductive bias, in general, increases sample efficiency and generalizability. Compositionality and incrementality can be obtained by building in particular types of structured inductive bias, in which the “knowledge” acquired through learning is decomposed into factors with independent semantics that can be combined to address exponentially more new problems ([ 5 ][5]). The idea of building in prior knowledge or structure is somewhat fraught. Richard Sutton, a pioneer of RL, asserted ([ 6 ][6]) that humans should not try to build any prior knowledge into a learning system because, historically, whenever we try to build something in, it has been wrong. His essay incited strong reactions ([ 7 ][7]), but it identified the critical question in the design of a system that learns: What kinds of inductive bias can be built into a learning system that will give it the leverage it needs to learn generalizable knowledge from a reasonable amount of data while not incapacitating it through inaccuracy or overconstraint? There are two intellectually coherent strategies for finding an appropriate bias, with different time scales and trade-offs, that can be used together to discover powerful and flexible prior structures for learning agents. One strategy is to use the techniques of machine learning at the “meta” level—that is, to use machine learning offline at system design time (in the robot “factory”) to discover the structures, algorithms, and prior knowledge that will enable it to learn efficiently online when it is deployed (in the “wild”). The basic idea of meta-learning has been present in machine learning and statistics since at least the 1980s ([ 8 ][8]). The fundamental idea is that in the factory, the meta-learning process has access to many samples of possible tasks or environments that the system might be confronted with in the wild. Rather than trying to learn strategies that are good for an individual environment, or even a single strategy that works well in all the environments, a meta-learner tries to learn a learning algorithm that, when faced with a new task or environment in the wild, will learn as efficiently and effectively as possible. It can do this by inducing the commonalities among the training tasks and using them to form a strong prior or inductive bias that allows the agent in the wild to learn only the aspects that differentiate the new task from the training tasks. Meta-learning can be very beautifully and generally formalized as a type of hierarchical Bayesian (probabilistic) inference ([ 9 ][9]) in which the training tasks can be seen as providing evidence about what the task in the wild will be like, and using that evidence to leverage data obtained in the wild. The Bayesian view can be computationally difficult to realize, however, because it requires reasoning over the large ensemble of tasks experienced in the factory that might potentially include the actual task in the wild. Another approach is to explicitly characterize meta-learning as two nested optimization problems. The inner optimization happens in the wild: The agent tries to find the hypothesis from some set of hypotheses generated in the factory that has the best “score” on the data it has in the wild. This inner optimization is characterized by the hypothesis space, the scoring metric, and the computer algorithm that will be used to search for the best hypothesis. In traditional machine learning, these ingredients are supplied by a human engineer. In meta-learning, at least some aspects are instead supplied by an outer “meta” optimization process that takes place in the factory. Meta-optimization tries to find parameters of the inner learning process itself that will enable the learning to work well in new environments that were drawn from the same distribution as the ones that were used for meta-learning. Recently, a useful formulation of meta-learning, called “model-agnostic meta-learning” (MAML), has been reported ([ 10 ][10]). MAML is a nested optimization framework in which the outer optimization selects initial values of some internal neural network weights that will be further adjusted by a standard gradient-descent optimization method in the wild. The RL2 algorithm ([ 11 ][11]) uses DRL in the factory to learn a general small program that runs in the wild but does not necessarily have the form of a machine-learning program. Another variation ([ 12 ][12]) seeks to discover, in the factory, modular building blocks (such as small neural networks) that can be combined to solve problems presented in the wild. The process of evolution in nature can be considered an extreme version of meta-learning, in which nature searches a highly unconstrained space of possible learning algorithms for an animal. (Of course, in nature, the physiology of the agent can change as well.) The more flexibility there is in the inner optimization problem solved during a robot's lifetime, the more resources—including example environments in the factory, broken robots in the wild, and computing capacity in both phases—are needed to learn robustly. In some ways, this returns us to the initial problem. Standard RL was rejected because, although it is a general-purpose learning method, it requires an enormous amount of experience in the wild. However, meta-RL requires substantial experience in the factory, which could make development infeasibly slow and costly. Thus, perhaps meta-learning is not a good solution, either. What is left? There are a variety of good directions to turn, including teaching by humans, collaborative learning with other robots, and changing the robot hardware along with the software. In all these cases, it remains important to design an effective methodology for developing robot software. Applying insights gained from computer science and engineering together with inspiration from cognitive neuroscience can help to find algorithms and structures that can be built into learning agents and provide leverage to learning both in the factory and in the wild. A paradigmatic example of this approach has been the development of convolutional neural networks ([ 13 ][13]). The idea is to design a neural network for processing images in such a way that it performs “convolutions”—local processing of patches of the image using the same computational pattern across the whole image. This design simultaneously encodes the prior knowledge that objects have basically the same appearance no matter where they are in an image (translation invariance) and the knowledge that groups of nearby pixels are jointly informative about the content of the image (spatial locality). Designing a neural network in this way means that it requires a much smaller number of parameters, and hence much less training, than doing so without convolutional structure. The idea of image convolution comes from both engineers and nature. It was a foundational concept in early signal processing and computer vision ([ 14 ][14]), and it has long been understood that there are cells in the mammalian visual cortex that seem to be performing a similar kind of computation ([ 15 ][15]). It is necessary to discover more ideas like convolution—that is, fundamental structural or algorithmic constraints that provide substantial leverage for learning but will not prevent robots from reaching their potential for generally intelligent behavior. Some candidate ideas include the ability to do some form of forward search using a “mental model” of the effects of actions, similar to planning or reasoning; the ability to learn and represent knowledge that is abstracted away from individual objects but can be applied much more generally (e.g., for all A and B, if A is on top of B and I move B, then A will probably move too); and the ability to reason about three-dimensional space, including planning and executing motions through it as well as using it as an organizing principle for memory. There are likely many other such plausible candidate principles. Many other problems will also need to be addressed, including how to develop infrastructure for training both in the factory and in the wild, as well as methodologies for helping humans to specify the rewards and for maintaining safety. It will be through a combination of engineering principles, biological inspiration, learning in the factory, and ultimately learning in the wild that generally intelligent robots can finally be created. 1. [↵][16]1. A. Barto, 2. R. S. Sutton, 3. C. W. Anderson , IEEE Trans. Syst. Man Cybern. 13, 834 (1983). [OpenUrl][17][CrossRef][18][Web of Science][19] 2. [↵][20]1. D. Silver et al ., Science 362, 1140 (2018). [OpenUrl][21][Abstract/FREE Full Text][22] 3. [↵][23]OpenAI, arXiv 1910.07113 (2019). 4. [↵][24]1. M. Belkin, 2. D. Hsu, 3. S. Ma, 4. S. Mandal , Proc. Natl. Acad. Sci. U.S.A. 116, 15849 (2019). [OpenUrl][25][Abstract/FREE Full Text][26] 5. [↵][27]1. P. W. Battaglia et al ., arXiv 1806.01261 (2018). 6. [↵][28]1. R. Sutton , “The bitter lesson”; [www.incompleteideas.net/IncIdeas/BitterLesson.html][29]. 7. [↵][30]1. R. Brooks , “A better lesson”; . 8. [↵][31]1. J. Schmidhuber , Evolutionary Principles in Self-Referential Learning (Technische Universität München, 1987). 9. [↵][32]1. D. Lindley, 2. A. F. M. Smith , J. R. Stat. Soc. B 34, 1 (1972). [OpenUrl][33] 10. [↵][34]1. C. Finn, 2. P. Abbeel, 3. S. Levine , Proceedings of the 34th International Conference on Machine Learning (2017), pp. 1126–1135. 11. [↵][35]1. Y. Duan et al ., arXiv 1611.02779 (2016). 12. [↵][36]1. F. Alet et al ., Proc. Mach. Learn. Res. 87, 856 (2018). [OpenUrl][37] 13. [↵][38]1. Y. Lecun, 2. L. Bottou, 3. Y. Bengio, 4. P. Haffner , Proc. IEEE 86, 2278 (1998). [OpenUrl][39] 14. [↵][40]1. A. Rosenfeld , ACM Comput. Surv. 1, 147 (1969). [OpenUrl][41] 15. [↵][42]1. D. H. Hubel, 2. T. N. Wiesel , J. Physiol. 195, 215 (1968). [OpenUrl][43][CrossRef][44][PubMed][45][Web of Science][46] Acknowledgments: The author is supported by NSF, ONR, AFOSR, Honda Research, and IBM. I thank T. Lozano-Perez and students and colleagues in the CSAIL Embodied Intelligence group for insightful discussions. [1]: #ref-1 [2]: #ref-2 [3]: #ref-3 [4]: #ref-4 [5]: #ref-5 [6]: #ref-6 [7]: #ref-7 [8]: #ref-8 [9]: #ref-9 [10]: #ref-10 [11]: #ref-11 [12]: #ref-12 [13]: #ref-13 [14]: #ref-14 [15]: #ref-15 [16]: #xref-ref-1-1 "View reference 1 in text" [17]: {openurl}?query=rft.jtitle%253DIEEE%2BTrans.%2BSyst.%2BMan%2BCybern.%26rft.volume%253D13%26rft.spage%253D834%26rft_id%253Dinfo%253Adoi%252F10.1109%252FTSMC.1983.6313077%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [18]: /lookup/external-ref?access_num=10.1109/TSMC.1983.6313077&link_type=DOI [19]: /lookup/external-ref?access_num=A1983SC59500020&link_type=ISI [20]: #xref-ref-2-1 "View reference 2 in text" [21]: {openurl}?query=rft.jtitle%253DScience%26rft.stitle%253DScience%26rft.aulast%253DSilver%26rft.auinit1%253DD.%26rft.volume%253D362%26rft.issue%253D6419%26rft.spage%253D1140%26rft.epage%253D1144%26rft.atitle%253DA%2Bgeneral%2Breinforcement%2Blearning%2Balgorithm%2Bthat%2Bmasters%2Bchess%252C%2Bshogi%252C%2Band%2BGo%2Bthrough%2Bself-play%26rft_id%253Dinfo%253Adoi%252F10.1126%252Fscience.aar6404%26rft_id%253Dinfo%253Apmid%252F30523106%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [22]: /lookup/ijlink/YTozOntzOjQ6InBhdGgiO3M6MTQ6Ii9sb29rdXAvaWpsaW5rIjtzOjU6InF1ZXJ5IjthOjQ6e3M6ODoibGlua1R5cGUiO3M6NDoiQUJTVCI7czoxMToiam91cm5hbENvZGUiO3M6Mzoic2NpIjtzOjU6InJlc2lkIjtzOjEzOiIzNjIvNjQxOS8xMTQwIjtzOjQ6ImF0b20iO3M6MjI6Ii9zY2kvMzY5LzY1MDYvOTE1LmF0b20iO31zOjg6ImZyYWdtZW50IjtzOjA6IiI7fQ== [23]: #xref-ref-3-1 "View reference 3 in text" [24]: #xref-ref-4-1 "View reference 4 in text" [25]: {openurl}?query=rft.jtitle%253DProc.%2BNatl.%2BAcad.%2BSci.%2BU.S.A.%26rft_id%253Dinfo%253Adoi%252F10.1073%252Fpnas.1903070116%26rft_id%253Dinfo%253Apmid%252F31341078%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [26]: /lookup/ijlink/YTozOntzOjQ6InBhdGgiO3M6MTQ6Ii9sb29rdXAvaWpsaW5rIjtzOjU6InF1ZXJ5IjthOjQ6e3M6ODoibGlua1R5cGUiO3M6NDoiQUJTVCI7czoxMToiam91cm5hbENvZGUiO3M6NDoicG5hcyI7czo1OiJyZXNpZCI7czoxMjoiMTE2LzMyLzE1ODQ5IjtzOjQ6ImF0b20iO3M6MjI6Ii9zY2kvMzY5LzY1MDYvOTE1LmF0b20iO31zOjg6ImZyYWdtZW50IjtzOjA6IiI7fQ== [27]: #xref-ref-5-1 "View reference 5 in text" [28]: #xref-ref-6-1 "View reference 6 in text" [29]: http://www.incompleteideas.net/IncIdeas/BitterLesson.html [30]: #xref-ref-7-1 "View reference 7 in text" [31]: #xref-ref-8-1 "View reference 8 in text" [32]: #xref-ref-9-1 "View reference 9 in text" [33]: {openurl}?query=rft.jtitle%253DJ.%2BR.%2BStat.%2BSoc.%2BB%26rft.volume%253D34%26rft.spage%253D1%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [34]: #xref-ref-10-1 "View reference 10 in text" [35]: #xref-ref-11-1 "View reference 11 in text" [36]: #xref-ref-12-1 "View reference 12 in text" [37]: {openurl}?query=rft.jtitle%253DProc.%2BMach.%2BLearn.%2BRes.%26rft.volume%253D87%26rft.spage%253D856%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [38]: #xref-ref-13-1 "View reference 13 in text" [39]: {openurl}?query=rft.jtitle%253DProc.%2BIEEE%26rft.volume%253D86%26rft.spage%253D2278%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [40]: #xref-ref-14-1 "View reference 14 in text" [41]: {openurl}?query=rft.jtitle%253DACM%2BComput.%2BSurv.%26rft.volume%253D1%26rft.spage%253D147%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [42]: #xref-ref-15-1 "View reference 15 in text" [43]: {openurl}?query=rft.jtitle%253DThe%2BJournal%2Bof%2BPhysiology%26rft.stitle%253DJ.%2BPhysiol.%26rft.aulast%253DHubel%26rft.auinit1%253DD.%2BH.%26rft.volume%253D195%26rft.issue%253D1%26rft.spage%253D215%26rft.epage%253D243%26rft.atitle%253DReceptive%2Bfields%2Band%2Bfunctional%2Barchitecture%2Bof%2Bmonkey%2Bstriate%2Bcortex%26rft_id%253Dinfo%253Adoi%252F10.1113%252Fjphysiol.1968.sp008455%26rft_id%253Dinfo%253Apmid%252F4966457%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [44]: /lookup/external-ref?access_num=10.1113/jphysiol.1968.sp008455&link_type=DOI [45]: /lookup/external-ref?access_num=4966457&link_type=MED&atom=%2Fsci%2F369%2F6506%2F915.atom [46]: /lookup/external-ref?access_num=A1968A792100014&link_type=ISI

To improve evaluation efficiency, a team of researchers at Helmholtz Zentrum München and the University Hospital, LMU Munich, trained a deep neuronal network with almost 20,000 single cell images to classify them. Dr. med Karsten Spiekermann and Simone Schwarz from the Department of Medicine III, University Hospital, LMU Munich, used images which were extracted from blood smears of 100 patients suffering from the aggressive blood disease AML and 100 controls. The new AI-driven approach was then evaluated by comparing its performance with the accuracy of human experts. The result showed that the AI-driven solution is able to identify diagnostic blast cells at least as good as a trained cytologist expert. Deep learning algorithms for image processing require two things: first, an appropriate convolutional neural network architecture with hundreds of thousands of parameters; second, a sufficiently large amount of training data.

Of course we've all watched – and very much enjoyed! Obviously, they achieved this through an extraordinary talented team, a surplus of technical skills and a philosophy of attractive creative play. But did you know that artificial intelligence also played a big role in this success? Curious to see what insurers can learn from this provocative combination of creative skills and AI we met with Max Reckers, performance technology expert at AFC Ajax, and before that at Bayern Munchen, Manchester United and the Dutch National Team. Max, just to set the stage; using data, algorithms, AI, performance technology … Why is Ajax doing all this?

A new artificial intelligence could help sort normal cells from diseased cells, researchers report in a new study. The Human Cell Atlas is a deep learning algorithm method that uses single-cell RNA sequencing to distinguish activated and deactivated cells within humans at any point, according to a study published Wednesday in Nature Communications. The ability to pinpoint healthy cells from diseased cells at a given time within a person's life cycle. "From a methodological point of view, this represents an enormous leap forward. Previously, such data could only be obtained from large groups of cells because the measurements required so much RNA," Maren Büttner, a researcher at the Institute of Computational Biology of the Helmholtz Zentrum München, said in a news release.

Modern technology makes it possible to sequence individual cells and to identify which genes are currently being expressed in each cell. These methods are sensitive and consequently error prone. Devices, environment and biology itself can be responsible for failures and differences between measurements. Researchers at Helmholtz Zentrum München joined forces with colleagues from the Technical University of Munich (TUM) and the British Wellcome Sanger Institute and have developed algorithms that make it possible to predict and correct such sources of error. The work was published in'Nature Methods' and'Nature Communications'.

SELF-A TTENTION EQUIPPED GRAPH CONVOLUTIONS FOR DISEASE PREDICTION Anees Kazi 1, S.Arvind krishna 2, Shayan Shekarforoush 3, Karsten Kortuem 4, Shadi Albarqouni 1, Nassir Navab 1, 5 1 Computer Aided Medical Procedures, Technische Universität München, Germany 2 National Institute of Technology Tiruchirappalli, India 3 Sharif University of Technology, Iran 4 Augenklinik der Universität, Klinikum der Universität München, Germany 5 Johns Hopkins University, Baltimore MD, USA ABSTRACT Multi-modal data comprising imaging (MRI, fMRI, PET, etc.) and non-imaging (clinical test, demographics, etc.) data can be collected together and used for disease prediction. Such diverse data gives complementary information about the patient's condition to make an informed diagnosis. A model capable of leveraging the individuality of each multi-modal data is required for better disease prediction. We propose a graph convolution based deep model which takes into account the distinctiveness of each element of the multi-modal data. We incorporate a novel self-attention layer, which weights every element of the demographic data by exploring its relation to the underlying disease.

Artificial intelligence has been a hot subject in real estate for a few years now and while some remain uncomfortable with the fast-growing trend, others are already saving time and money by using such technologies in their businesses. While AI has its challenges, the potential gains for the industry far outweigh them. In one of the opening panels of 2018's Expo Real, the yearly international real estate and investment conference taking place in München, Bastian Schulz, head of sales at Leverton; Sascha Donner, co-founder & head of product at startup Evana; Matthew Webster, CFO of Cloudscraper; and Nicolai Wendland, COO of 21st Real Estate, shared their vision on how AI could shape the industry. The highest goal for real estate professionals using AI seems to be the simplification of the acquisition process, at a larger scale. "There is no bigger vision than imagining the process of purchasing one property with one click, like we do with shares. We will be there soon, in a few years," Wendland said.