We consider the application of deep generative models in propagating uncertainty through complex physical systems. Specifically, we put forth an implicit variational inference formulation that constrains the generative model output to satisfy given physical laws expressed by partial differential equations. Such physics-informed constraints provide a regularization mechanism for effectively training deep probabilistic models for modeling physical systems in which the cost of data acquisition is high and training data-sets are typically small. This provides a scalable framework for characterizing uncertainty in the outputs of physical systems due to randomness in their inputs or noise in their observations. We demonstrate the effectiveness of our approach through a canonical example in transport dynamics.

Fetal brain imaging is a cornerstone of prenatal screening and early diagnosis of congenital anomalies. Knowledge of fetal gestational age is the key to the accurate assessment of brain development. This study develops an attention-based deep learning model to predict gestational age of the fetal brain. The proposed model is an end-to-end framework that combines key insights from multi-view MRI including axial, coronal, and sagittal views. The model also uses age-activated weakly-supervised attention maps to enable rotation-invariant localization of the fetal brain among background noise. We evaluate our methods on the collected fetal brain MRI cohort with a large age distribution from 125 to 273 days. Our extensive experiments show age prediction performance with R2 = 0.94 using multi-view MRI and attention.

Conventional methods for visual assessment of civil infrastructures have certain limitations, such as subjectivity of the collected data, long inspection time, and high cost of labor. Although some new technologies i.e. robotic techniques that are currently in practice can collect objective, quantified data, the inspectors own expertise is still critical in many instances since these technologies are not designed to work interactively with human inspector. This study aims to create a smart, human centered method that offers significant contributions to infrastructure inspection, maintenance, management practice, and safety for the bridge owners. By developing a smart Mixed Reality framework, which can be integrated into a wearable holographic headset device, a bridge inspector, for example, can automatically analyze a certain defect such as a crack that he or she sees on an element, display its dimension information in real-time along with the condition state. Such systems can potentially decrease the time and cost of infrastructure inspections by accelerating essential tasks of the inspector such as defect measurement, condition assessment and data processing to management systems. The human centered artificial intelligence will help the inspector collect more quantified and objective data while incorporating inspectors professional judgement. This study explains in detail the described system and related methodologies of implementing attention guided semi supervised deep learning into mixed reality technology, which interacts with the human inspector during assessment. Thereby, the inspector and the AI will collaborate or communicate for improved visual inspection.

Long Short-Term Memory (LSTM) neural network is an enhanced Recurrent Neural Network (RNN) that has gained significant attention in recent years. It solved the vanishing and exploding gradient problems that a standard RNN has and was successfully applied to a variety of time-series forecasting problems. In power systems, distribution feeder long-term load forecast is a critical task many electric utility companies perform on an annual basis. The goal of this task is to forecast the load change on existing distribution feeders for the next few years. The forecasted results will be used as input in long-term system planning studies to determine necessary system upgrades so that the distribution system can continue to operate reliably during normal operation and contingences. This research proposed a comprehensive hybrid model based on LSTM neural network for this classic and important forecasting task. It is not only able to combine the advantages of top-down and bottom-up forecasting models but also able to leverage the time-series characteristics of multi-year data. This paper firstly explains the concept of LSTM neural network and then discusses the steps of feature selection, feature engineering and model establishment in detail. In the end, a real-world application example for a large urban grid in West Canada is provided. The results are compared to other models such as bottom-up, ARIMA and ANN. The proposed model demonstrates superior performance and great practicality for forecasting long-term peak demand for distribution feeders.

We derive the fast convergence rates of a deep neural network (DNN) classifier with the rectified linear unit (ReLU) activation function learned using the hinge loss. We consider three cases for a true model: (1) a smooth decision boundary, (2) smooth conditional class probability, and (3) the margin condition (i.e., the probability of inputs near the decision boundary is small). We show that the DNN classifier learned using the hinge loss achieves fast rate convergences for all three cases provided that the architecture (i.e., the number of layers, number of nodes and sparsity). is carefully selected. An important implication is that DNN architectures are very flexible for use in various cases without much modification. In addition, we consider a DNN classifier learned by minimizing the cross-entropy, and show that the DNN classifier achieves a fast convergence rate under the condition that the conditional class probabilities of most data are sufficiently close to either 1 or zero. This assumption is not unusual for image recognition because human beings are extremely good at recognizing most images. To confirm our theoretical explanation, we present the results of a small numerical study conducted to compare the hinge loss and cross-entropy.

In this paper, we leverage the efficiency of Binarized Neural Networks (BNNs) to learn complex state transition models of planning domains with discretized factored state and action spaces. In order to directly exploit this transition structure for planning, we present two novel compilations of the learned factored planningproblem with BNNs based on reductions to Weighted Partial Maximum Boolean Satisfiability (FD-SAT-Plan) as well as Binary Linear Programming (FD-BLP-Plan).Theoretically, we show that our SATbased Bi-Directional Neuron Activation Encoding is asymptotically the most compact encoding in the literature and maintains the generalized arc-consistency property throughunit propagation - an important property that facilitates efficiency in SAT solvers. Experimentally, we validate the computational efficiency of our Bi-Directional Neuron Activation Encoding in comparison to an existing neuron activationencoding and demonstrate the effectiveness of learning complex transition models with BNNs. We test the runtime efficiency of both FD-SAT- Plan and FD-BLP-Plan on the learned factored planning problem showing that FD-SAT-Plan scales better with increasing BNN size and complexity. Parts of this work appeared in preliminary form in Say and Sanner, 2018 [1]. Preprint submitted to AIJ December 11, 2018 our encodings through simulated or real-world interaction. Keywords: data-driven planning, binarized neural networks, Weighted Partial Maximum Boolean Satisfiability, Binary Linear Programming 1. Introduction Deep neural networks (DNNs) have significantly improved the ability of autonomous systemsto perform complex tasks, such as image recognition [2], speech recognition [3] and natural language processing [4], and can outperform humans and human-designed superhuman systems in complex planning tasks such as Go [5] and Chess [6]. In the area of learning and planning, recent work on HD-MILP-Plan [7] has explored a two-stage framework that (i) learns transitions models from data with ReLUbased DNNs and (ii) plans optimally with respect to the learned transition models using Mixed-Integer Linear Programming, but did not provide encodingsthat are able to learn and plan with discrete state variables.

In this latest Data Science Central webinar, we will cover the principles for training your neural network including activation and loss functions, batch sizes, data normalization, and validation datasets. All these concepts will be brought to life by demonstrating how Databricks simplifies deep learning - letting you quickly access ready-to-use ML environments, as well as prepare data, and train models faster. After this session, if requested, you will receive the presentation and associated notebooks so you can run the samples yourself.

DeepMind's artificial intelligence programme AlphaZero is now showing signs of human-like intuition and creativity, in what developers have hailed as'turning point' in history. The computer system amazed the world last year when it mastered the game of chess from scratch within just four hours, despite not being programmed how to win. But now, after a year of testing and analysis by chess grandmasters, the machine has developed a new style of play unlike anything ever seen before, suggesting the programme is now improvising like a human. Unlike the world's best chess machine - Stockfish - which calculates millions of possible outcomes as it plays, AlphaZero learns from its past successes and failures, making its moves based on, a'nebulous sense that it is all going to work out in the long run,' according to experts at DeepMind. When AlphaZero was pitted against Stockfish in 1,000 games, it lost just six, winning convincingly 155 times, and drawing the remaining bouts.

In case the text is composed of speech, speech-to-text conversion is performed.

I really want to take good care of the reader. That's why from time to time, you can expect articles focused only on theory. Because long articles discourage from learning, I will keep them at 5–8 minutes of reading time. I cannot just put everything into a single article -- code snippets, math, terminology -- because that would result in reducing the explanations of essential concepts. I believe that dividing the knowledge into smaller parts and expanding it across more articles will make the learning process smooth as there will be no need to take stops and detours.