World wide road traffic fatality and accident rates are high, and this is true even in technologically advanced countries like the USA. Despite the advances in Intelligent Transportation Systems, safe transportation routing i.e., finding safest routes is largely an overlooked paradigm. In recent years, large amount of traffic data has been produced by people, Internet of Vehicles and Internet of Things (IoT). Also, thanks to advances in cloud computing and proliferation of mobile communication technologies, it is now possible to perform analysis on vast amount of generated data (crowd sourced) and deliver the result back to users in real time. This paper proposes SafeRNet, a safe route computation framework which takes advantage of these technologies to analyze streaming traffic data and historical data to effectively infer safe routes and deliver them back to users in real time. SafeRNet utilizes Bayesian network to formulate safe route model. Furthermore, a case study is presented to demonstrate the effectiveness of our approach using real traffic data. SafeRNet intends to improve drivers safety in a modern technology rich transportation system.

The Multimedia Neural Cognitive Computing (MNCC) model was designed based on the nervous mechanism and cognitive architecture. Furthermore, the semantic-oriented hierarchical Cross-media Neural Cognitive Computing (CNCC) framework was proposed based on MNCC, and formal description and analysis for CNCC was given. It would effectively improve the performance of semantic processing for multimedia information, and has far-reaching significance for exploration and realization brain-inspired computing. Keywords Deep learning·cognitive computing·brain-inspired computing·cross-media neural cognitive computing·multimedia neural cognitive computing 1 Introduction The brain-inspired computing (BIC) is the integration of neural cognitive science and information technology. It would realize state-of-the-art computing system which has advanced in energy consumption, computing ability and efficiency.

The algorithm selection problem is to choose the most suitable algorithm for solving a given problem instance and thus, it leverages the complementarity between different approaches that is present in many areas of AI. We report on the state of the art in algorithm selection, as defined by the Algorithm Selection Competition series 2015 to 2017. The results of these competitions show how the state of the art improved over the years. Although performance in some cases is very promising, there is still room for improvement in other cases. Finally, we provide insights into why some scenarios are hard, and pose challenges to the community on how to advance the current state of the art. Keywords: 1. Introduction Algorithm Selection, Meta-Learning, Competition Analysis In many areas of AI, there are different algorithms to solve the same type of problem. Often, these algorithms are complementary in the sense that one algorithm works well when others fail and vice versa. For example in propositional satisfiability solving (SAT), there are complete tree-based solvers aimed at structured, industrial-like problems, and local search solvers aimed at randomly generated problems. In many practical cases, the performance difference between algorithms can be very large, for example as shown by Xu et al. (2012) for SAT. Per-instance algorithm selection (Rice, 1976) is a way to leverage this complementarity between different algorithms.

In the context of tree-search stochastic planning algorithms where a generative model is available, we consider on-line planning algorithms building trees in order to recommend an action. We investigate the question of avoiding re-planning in subsequent decision steps by directly using sub-trees as action recommender. Firstly, we propose a method for open loop control via a new algorithm taking the decision of re-planning or not at each time step based on an analysis of the statistics of the sub-tree. Secondly, we show that the probability of selecting a suboptimal action at any depth of the tree can be upper bounded and converges towards zero. Moreover, this upper bound decays in a logarithmic way between subsequent depths. This leads to a distinction between node-wise optimality and state-wise optimality. Finally, we empirically demonstrate that our method achieves a compromise between loss of performance and computational gain.

This paper introduces Random Multimodel Deep Learning (RMDL): a new ensemble, deep learning approach for classification. Deep learning models have achieved state-of-the-art results across many domains. RMDL solves the problem of finding the best deep learning structure and architecture while simultaneously improving robustness and accuracy through ensembles of deep learning architectures. RDML can accept as input a variety data to include text, video, images, and symbolic. This paper describes RMDL and shows test results for image and text data including MNIST, CIFAR-10, WOS, Reuters, IMDB, and 20newsgroup. These test results show that RDML produces consistently better performance than standard methods over a broad range of data types and classification problems.

The framework of reinforcement learning or optimal control provides a mathematical formalization of intelligent decision making that is powerful and broadly applicable. While the general form of the reinforcement learning problem enables effective reasoning about uncertainty, the connection between reinforcement learning and inference in probabilistic models is not immediately obvious. However, such a connection has considerable value when it comes to algorithm design: formalizing a problem as probabilistic inference in principle allows us to bring to bear a wide array of approximate inference tools, extend the model in flexible and powerful ways, and reason about compositionality and partial observability. In this article, we will discuss how a generalization of the reinforcement learning or optimal control problem, which is sometimes termed maximum entropy reinforcement learning, is equivalent to exact probabilistic inference in the case of deterministic dynamics, and variational inference in the case of stochastic dynamics. We will present a detailed derivation of this framework, overview prior work that has drawn on this and related ideas to propose new reinforcement learning and control algorithms, and describe perspectives on future research.

Bayesian inference provides a principled approach towards uncertainty quantification of free parameters in geophysical forward models. This provides advantages over optimization methods that provide single point estimates as solutions, which lack uncertainty quantification. Badlands (basin and landscape dynamics model) is geophysical forward model that simulates topography development at various space and time scales. Badlands consists of a number of geophysical parameters that need to be estimated with appropriate uncertainty quantification, given the observed ground truth such as surface topography, sediment thickness and stratigraphy through time. This is challenging due to the scarcity of data, sensitivity of the parameters and complexity of the Badlands model. In this paper, we take a Bayesian approach to provide inference using Markov chain Monte Carlo sampling (MCMC). Hence, we present \textit{BayesLands}, a Bayesian framework for Badlands that fuses information obtained from complex forward models with observational data and prior knowledge. As a proof-of-concept, we consider a synthetic and real-world topography with two free parameters, namely precipitation and erodibility, that we need to estimate through BayesLands. The results of the experiments shows that BayesLands yields a promising distribution of the parameters. Moreover, the challenge in sampling due to multi-modality is presented through visualizing a likelihood surface that has a range of suboptimal modes.

This paper introduces a variational approximation framework using direct optimization of what is known as the {\it scale invariant Alpha-Beta divergence} (sAB divergence). This new objective encompasses most variational objectives that use the Kullback-Leibler, the R{\'e}nyi or the gamma divergences. It also gives access to objective functions never exploited before in the context of variational inference. This is achieved via two easy to interpret control parameters, which allow for a smooth interpolation over the divergence space while trading-off properties such as mass-covering of a target distribution and robustness to outliers in the data. Furthermore, the sAB variational objective can be optimized directly by repurposing existing methods for Monte Carlo computation of complex variational objectives, leading to estimates of the divergence instead of variational lower bounds. We show the advantages of this objective on Bayesian models for regression problems.

The non-stationary nature of electroencephalography (EEG) signals makes an EEG-based brain-computer interface (BCI) a dynamic system, thus improving its performance is a challenging task. In addition, it is well-known that due to non-stationarity based covariate shifts, the input data distributions of EEG-based BCI systems change during inter- and intra-session transitions, which poses great difficulty for developments of online adaptive data-driven systems. Ensemble learning approaches have been used previously to tackle this challenge. However, passive scheme based implementation leads to poor efficiency while increasing high computational cost. This paper presents a novel integration of covariate shift estimation and unsupervised adaptive ensemble learning (CSE-UAEL) to tackle non-stationarity in motor-imagery (MI) related EEG classification. The proposed method first employs an exponentially weighted moving average model to detect the covariate shifts in the common spatial pattern features extracted from MI related brain responses. Then, a classifier ensemble was created and updated over time to account for changes in streaming input data distribution wherein new classifiers are added to the ensemble in accordance with estimated shifts. Furthermore, using two publicly available BCI-related EEG datasets, the proposed method was extensively compared with the state-of-the-art single-classifier based passive scheme, single-classifier based active scheme and ensemble based passive schemes. The experimental results show that the proposed active scheme based ensemble learning algorithm significantly enhances the BCI performance in MI classifications.

There is currently great interest in applying neural networks to prediction tasks in medicine. It is important for predictive models to be able to use survival data, where each patient has a known follow-up time and event/censoring indicator. This avoids information loss when training the model and enables generation of predicted survival curves. In this paper, we describe a discrete-time survival model that is designed to be used with neural networks. The model is trained with the maximum likelihood method using minibatch stochastic gradient descent (SGD). The use of SGD enables rapid training speed. The model is flexible, so that the baseline hazard rate and the effect of the input data can vary with follow-up time. It has been implemented in the Keras deep learning framework, and source code for the model and several examples is available online. We demonstrated the high performance of the model by using it as part of a convolutional neural network to predict survival for over 10,000 patients with metastatic cancer, using the full text of 1,137,317 provider notes. The model's C-index on the validation set was 0.71, which was superior to a linear baseline model (C-index 0.69).