We develop a proxy model based on deep learning methods to accelerate the simulations of oil reservoirs--by three orders of magnitude--compared to industry-strength physics-based PDE solvers. This paper describes a new architectural approach to this task, accompanied by a thorough experimental evaluation on a publicly available reservoir model. We demonstrate that in a practical setting a speedup of more than 2000X can be achieved with an average sequence error of about 10\% relative to the oil-field simulator. The proxy model is contrasted with a high-quality physics-based acceleration baseline and is shown to outperform it by several orders of magnitude. We believe the outcomes presented here are extremely promising and offer a valuable benchmark for continuing research in oil field development optimization. Due to its domain-agnostic architecture, the presented approach can be extended to many applications beyond the field of oil and gas exploration.

Conventional automated segmentation of the human head distinguishes different tissues based on image intensities in an MRI volume and prior tissue probability maps (TPM). This works well for normal head anatomies, but fails in the presence of unexpected lesions. Deep convolutional neural networks leverage instead volumetric spatial patterns and can be trained to segment lesions, but have thus far not integrated prior probabilities. Here we add to a three-dimensional convolutional network spatial priors with a TPM, morphological priors with conditional random fields, and context with a wider field-of-view at lower resolution. The new architecture, which we call MultiPrior, was designed to be a fully-trainable, three-dimensional convolutional network. Thus, the resulting architecture represents a neural network with learnable spatial memories. When trained on a set of stroke patients and healthy subjects, MultiPrior outperforms the state-of-the-art segmentation tools such as DeepMedic and SPM segmentation. The approach is further demonstrated on patients with disorders of consciousness, where we find that cognitive state correlates positively with gray-matter volumes and negatively with the extent of ventricles. We make the code and trained networks freely available to support future clinical research projects.

The Organisation for Economic Co-operation and Development unveiled the first intergovernmental standard for artificial intelligence policies Wednesday--and the organization's 36 member countries including America have initially signed on along with Argentina, Brazil, Colombia, Costa Rica, Peru and Romania. OECD, an international forum that unites stakeholders from many nations to work together to address challenges of globalization, released "Recommendations of the Council on Artificial Intelligence" to help foster a global policy ecosystem that leverages the evolving technology's benefits, while also protecting human rights and democratic values. OECD's Director of the Science, Technology and Innovation Directorate Andrew Wyckoff told reporters that the principles' creators hope they'll help shape a stable regulatory environment that promotes the tech's positive uses, while withstanding unethical abuses. "AI is what we would call a'general purpose technology.' It's going to change the way we do things in nearly every single sector of the economy--that's part of the reason we give so much importance to its development," he said.

We consider a blind identification problem in which we aim to recover a statistical model of a network without knowledge of the network's edges, but based solely on nodal observations of a certain process. More concretely, we focus on observations that consist of snapshots of a diffusive process that evolves over the unknown network. We model the network as generated from an independent draw from a latent stochastic block model (SBM), and our goal is to infer both the partition of the nodes into blocks, as well as the parameters of this SBM. We present simple spectral algorithms that provably solve the partition recovery and parameter estimation problems with high accuracy. Our analysis relies on recent results in random matrix theory and covariance estimation, and associated concentration inequalities. We illustrate our results with several numerical experiments.

The Planet dataset has become a standard computer vision benchmark that involves classifying or tagging the contents satellite photos of Amazon tropical rainforest. The dataset was the basis of a data science competition on the Kaggle website and was effectively solved. Nevertheless, it can be used as the basis for learning and practicing how to develop, evaluate, and use convolutional deep learning neural networks for image classification from scratch. This includes how to develop a robust test harness for estimating the performance of the model, how to explore improvements to the model, and how to save the model and later load it to make predictions on new data. In this tutorial, you will discover how to develop a convolutional neural network to classify satellite photos of the Amazon tropical rainforest. How to Develop a Convolutional Neural Network to Classify Satellite Photos of the Amazon Rainforest Photo by Anna & Michal, some rights reserved. The "Planet: Understanding the Amazon from Space" competition was held on Kaggle in 2017. The competition involved classifying small squares of satellite images taken from space of the Amazon rainforest in Brazil in terms of 17 classes, such as "agriculture", "clear", and "water". Given the name of the competition, the dataset is often referred to simply as the "Planet dataset". The color images were provided in both TIFF and JPEG format with the size 256 256 pixels. A total of 40,779 images were provided in the training dataset and 40,669 images were provided in the test set for which predictions were required. The problem is an example of a multi-label image classification task, where one or more class labels must be predicted for each label. This is different from multi-class classification, where each image is assigned one from among many classes. The multiple class labels were provided for each image in the training dataset with an accompanying file that mapped the image filename to the string class labels. The competition was run for approximately four months (April to July in 2017) and a total of 938 teams participated, generating much discussion around the use of data preparation, data augmentation, and the use of convolutional neural networks.

I recently was a guest speaker at the Stanford AI Salon on the topic of accessiblity in AI, which included a free-ranging discussion among assembled members of the Stanford AI Lab. There were a number of interesting questions and topics, so I thought I would share a few of my answers here. Q: What 3 things would you most like the general public to know about AI? AI is easier to use than the hype would lead you to believe. In my recent talk at the MIT Technology Review conference, I debunked several common myths that you must have a PhD, a giant data set, or expensive computational power to use AI. Most AI researchers are not working on getting computers to achieve human consciousness.

This article proposes a biologically inspired neurocomputational architecture which learns associations between words and referents in different contexts, considering evidence collected from the literature of Psycholinguistics and Neurolinguistics. The multi-layered architecture takes as input raw images of objects (referents) and streams of word's phonemes (labels), builds an adequate representation, recognizes the current context, and associates label with referents incrementally, by employing a Self-Organizing Map which creates new association nodes (prototypes) as required, adjusts the existing prototypes to better represent the input stimuli and removes prototypes that become obsolete/unused. The model takes into account the current context to retrieve the correct meaning of words with multiple meanings. Simulations show that the model can reach up to 78% of word-referent association accuracy in ambiguous situations and approximates well the learning rates of humans as reported by three different authors in five Cross-Situational Word Learning experiments, also displaying similar learning patterns in the different learning conditions.

Deep neural networks (DNNs) have been quite successful in solving many complex learning problems. However, DNNs tend to have a large number of learning parameters, leading to a large memory and computation requirement. In this paper, we propose a model compression framework for efficient training and inference of deep neural networks on embedded systems. Our framework provides data structures and kernels for OpenCL-based parallel forward and backward computation in a compressed form. In particular, our method learns sparse representations of parameters using $\ell_1$-based sparse coding while training, storing them in compressed sparse matrices. Unlike the previous works, our method does not require a pre-trained model as an input and therefore can be more versatile for different application environments. Even though the use of $\ell_1$-based sparse coding for model compression is not new, we show that it can be far more effective than previously reported when we use proximal point algorithms and the technique of debiasing. Our experiments show that our method can produce minimal learning models suitable for small embedded devices.

We present a graph-based semi-supervised learning (SSL) method for learning edge flows defined on a graph. Specifically, given flow measurements on a subset of edges, we want to predict the flows on the remaining edges. To this end, we develop a computational framework that imposes certain constraints on the overall flows, such as (approximate) flow conservation. These constraints render our approach different from classical graph-based SSL for vertex labels, which posits that tightly connected nodes share similar labels and leverages the graph structure accordingly to extrapolate from a few vertex labels to the unlabeled vertices. We derive bounds for our method's reconstruction error and demonstrate its strong performance on synthetic and real-world flow networks from transportation, physical infrastructure, and the Web. Furthermore, we provide two active learning algorithms for selecting informative edges on which to measure flow, which has applications for optimal sensor deployment. The first strategy selects edges to minimize the reconstruction error bound and works well on flows that are approximately divergence-free. The second approach clusters the graph and selects bottleneck edges that cross cluster-boundaries, which works well on flows with global trends.

The field of collaborative interactive learning (CIL) aims at developing and investigating the technological foundations for a new generation of smart systems that support humans in their everyday life. While the concept of CIL has already been carved out in detail (including the fields of dedicated CIL and opportunistic CIL) and many research objectives have been stated, there is still the need to clarify some terms such as information, knowledge, and experience in the context of CIL and to differentiate CIL from recent and ongoing research in related fields such as active learning, collaborative learning, and others. Both aspects are addressed in this paper.