This paper presents an integrated methodology supporting decisions in urban planning. In particular, it deals with the prioritization and the selection of a portfolio of projects related to buildings of some values for the cultural heritage in cities. More precisely, our methodology has been validated to the historical center of Naples, Italy. Each project is assessed on the basis of a set of both quantitative and qualitative criteria with the purpose to determine their level of priority for further selection. This step was performed through the application of the Electre Tri-nC method which is a multiple criteria outranking based method for ordinal classification (or sorting) problems and allows to assign a priority level to each project as an analytical "recommendation" tool. To identify the efficient portfolios and to support the selection of the most adequate set of projects to activate, a set of resources (namely budgetary constraints) as well as some logical constraints related to urban policy requirements have to be taken into consideration together with the priority of projects in a portfolio analysis model. The process has been conducted by means of the interaction between analysts, municipality representative and experts. The proposed methodology is generic enough to be applied to other territorial or urban planning problems. We strongly believe that, given the increasing interest of historical cities to restore their cultural heritage, the integrated multiple criteria decision aiding analytical tool proposed in this paper has significant potential to be used in the future.

Step sizes in neural network training are largely determined using predetermined rules such as fixed learning rates and learning rate schedules, which require user input to determine their functional form and associated hyperparameters. Global optimization strategies to resolve these hyperparameters are computationally expensive. Line searches are capable of adaptively resolving learning rate schedules. However, due to discontinuities induced by mini-batch sampling, they have largely fallen out of favor. Notwithstanding, probabilistic line searches have recently demonstrated viability in resolving learning rates for stochastic loss functions. This method creates surrogates with confidence intervals, where restrictions are placed on the rate at which the search domain can grow along a search direction. This paper introduces an alternative paradigm, Gradient-Only Line Searches that are inexact (GOLS-I), as an alternative strategy to automatically resolve learning rates in stochastic cost functions over a range of 15 orders of magnitude without the use of surrogates. We show that GOLS-I is a competitive strategy to reliably resolve step sizes, adding high value in terms of performance, while being easy to implement. Considering mini-batch sampling, we open the discussion on how to split the effort to resolve quality search directions from quality step size estimates along a search direction.

Weighted model integration (WMI) extends Weighted model counting (WMC) to the integration of functions over mixed discrete-continuous domains. It has shown tremendous promise for solving inference problems in graphical models and probabilistic programming. Yet, state-of-the-art tools for WMI are limited in terms of performance and ignore the independence structure that is crucial to improving efficiency. To address this limitation, we propose an efficient model integration algorithm for theories with tree primal graphs. We exploit the sparse graph structure by using search to performing integration. Our algorithm greatly improves the computational efficiency on such problems and exploits context-specific independence between variables. Experimental results show dramatic speedups compared to existing WMI solvers on problems with tree-shaped dependencies.

This work is motivated by multimodality breast cancer imaging data, which is quite challenging in that the signals of discrete tumor-associated microvesicles (TMVs) are randomly distributed with heterogeneous patterns. This imposes a significant challenge for conventional imaging regression and dimension reduction models assuming a homogeneous feature structure. We develop an innovative multilayer tensor learning method to incorporate heterogeneity to a higher-order tensor decomposition and predict disease status effectively through utilizing subject-wise imaging features and multimodality information. Specifically, we construct a multilayer decomposition which leverages an individualized imaging layer in addition to a modality-specific tensor structure. One major advantage of our approach is that we are able to efficiently capture the heterogeneous spatial features of signals that are not characterized by a population structure as well as integrating multimodality information simultaneously. To achieve scalable computing, we develop a new bi-level block improvement algorithm. In theory, we investigate both the algorithm convergence property, tensor signal recovery error bound and asymptotic consistency for prediction model estimation. We also apply the proposed method for simulated and human breast cancer imaging data. Numerical results demonstrate that the proposed method outperforms other existing competing methods.

In numerical modeling of the Earth System, many processes remain unknown or ill represented (let us quote sub-grid processes, the dependence to unknown latent variables or the non-inclusion of complex dynamics in numerical models) but sometimes can be observed. This paper proposes a methodology to produce a hybrid model combining a physical-based model (forecasting the well-known processes) with a neural-net model trained from observations (forecasting the remaining processes). The approach is applied to a shallow-water model in which the forcing, dissipative and diffusive terms are assumed to be unknown. We show that the hybrid model is able to reproduce with great accuracy the unknown terms (correlation close to 1). For long term simulations it reproduces with no significant difference the mean state, the kinetic energy, the potential energy and the potential vorticity of the system. Lastly it is able to function with new forcings that were not encountered during the training phase of the neural network.

Multi-fidelity methods are prominently used when cheaply-obtained, but possibly biased and noisy, observations must be effectively combined with limited or expensive true data in order to construct reliable models. This arises in both fundamental machine learning procedures such as Bayesian optimization, as well as more practical science and engineering applications. In this paper we develop a novel multi-fidelity model which treats layers of a deep Gaussian process as fidelity levels, and uses a variational inference scheme to propagate uncertainty across them. This allows for capturing nonlinear correlations between fidelities with lower risk of overfitting than existing methods exploiting compositional structure, which are conversely burdened by structural assumptions and constraints. We show that the proposed approach makes substantial improvements in quantifying and propagating uncertainty in multi-fidelity set-ups, which in turn improves their effectiveness in decision making pipelines.

Although deep neural networks have achieved revolutionary success over various tasks, i.e., computer vision [He et al., 2016] and natural language understanding [Hochreiter and Schmidhuber, 1997], they are still in lack of a rigorous theoretical study of the optimization and generalization properties. Specifically for the optimization, because the loss of deep neural network is highly nonconvex, local search algorithms like gradient descent is hard to analyze with performance guarantee. Many recent works [Choromanska et al., 2015, Kawaguchi, 2016, Nguyen and Hein, 2017, Soudry and Hoffer, 2017] have studied the loss surface of the neural networks and a common claim is that (deep) neural networks have H. Zhang, W. Chen and TY Liu are with Microsoft Research Asia, Beijing, 100080 China (email: {huzhang, wche, tyliu}@microsoft.com); D. Yu is with School of Data and Computer Science at Sun Yat-sen University, Guangzhou, 510275, China (email: yuda3@mail2.sysu.edu.cn).

Video Friday is your weekly selection of awesome robotics videos, collected by your Automaton bloggers. We'll also be posting a weekly calendar of upcoming robotics events for the next few months; here's what we have so far (send us your events!): Let us know if you have suggestions for next week, and enjoy today's videos. This soft gripper from MIT is based on an origami "magic-ball." It's a "magic-ball gripper," and that hyphen placement is absolutely critical to it functioning appropriately.

With roughly the same population as the State of Missouri, Lebanon is a small country of six million people that borders Syria and Israel. Due to its location, the country has been subjected to a multitude of political and religious factions inhabiting the state. People frequently fight over whose invisible friend is better, and the country has faced long periods of instability including wars with Israel, civil wars and internal conflicts, and most recently some spillover from the Syrian war – which means lots of Syrians flying around on motorcycles. All of this turmoil has contributed to structural problems in the economy such as chronic fiscal deficits that have increased Lebanon's debt-to-GDP ratio to the third highest in the world. Economic growth has slowed to 1-2% over the past decade which constrains government investments in necessary infrastructure improvements. Notwithstanding these challenges, day to day life in Lebanon is pretty awesome.

This fall, Gabon was facing an odd and tenuous political situation. President Ali Bongo had been out of the country since October receiving medical treatment in Saudi Arabia and London and had not been seen in public. People in Gabon and observers outside the country were growing suspicious about the president's well being, and the government's lack of answers only fueled doubts; some even said he was dead. After months of little information, on December 9th, the country's vice president announced that Bongo had suffered a stroke in the autumn, but remained in good shape. Despite such assurances, civil society groups and many members of the public wondered why Bongo, if he was well, had not made any public appearances, save for a few pictures of him released by the government along with a silent video.