Then detection and identification of extreme weather events in large-scale climate simulations is an important problem for risk management, informing governmental policy decisions and advancing our basic understanding of the climate system. Recent work has shown that fully supervised convolutional neural networks (CNNs) can yield acceptable accuracy for classifying well-known types of extreme weather events when large amounts of labeled data are available. However, many different types of spatially localized climate patterns are of interest including hurricanes, extra-tropical cyclones, weather fronts, and blocking events among others. Existing labeled data for these patterns can be incomplete in various ways, such as covering only certain years or geographic areas and having false negatives. This type of climate data therefore poses a number of interesting machine learning challenges. We present a multichannel spatiotemporal CNN architecture for semi-supervised bounding box prediction and exploratory data analysis. We demonstrate that our approach is able to leverage temporal information and unlabeled data to improve the localization of extreme weather events. Further, we explore the representations learned by our model in order to better understand this important data. We present a dataset, ExtremeWeather, to encourage machine learning research in this area and to help facilitate further work in understanding and mitigating the effects of climate change. The dataset is available at extremeweatherdataset.github.io and the code is available at https://github.com/eracah/hur-detect.

Kernel methods are powerful tools to capture nonlinear patterns behind data. They implicitly learn high (even infinite) dimensional nonlinear features in the Reproducing Kernel Hilbert Space (RKHS) while making the computation tractable by leveraging the kernel trick. Classic kernel methods learn a single layer of nonlinear features, whose representational power may be limited. Motivated by recent success of deep neural networks (DNNs) that learn multi-layer hierarchical representations, we propose a Stacked Kernel Network (SKN) that learns a hierarchy of RKHS-based nonlinear features. SKN interleaves several layers of nonlinear transformations (from a linear space to a RKHS) and linear transformations (from a RKHS to a linear space). Similar to DNNs, a SKN is composed of multiple layers of hidden units, but each parameterized by a RKHS function rather than a finite-dimensional vector. We propose three ways to represent the RKHS functions in SKN: (1)nonparametric representation, (2)parametric representation and (3)random Fourier feature representation. Furthermore, we expand SKN into CNN architecture called Stacked Kernel Convolutional Network (SKCN). SKCN learning a hierarchy of RKHS-based nonlinear features by convolutional operation with each filter also parameterized by a RKHS function rather than a finite-dimensional matrix in CNN, which is suitable for image inputs. Experiments on various datasets demonstrate the effectiveness of SKN and SKCN, which outperform the competitive methods.

In representation learning (RL), how to make the learned representations easy to interpret and less overfitted to training data are two important but challenging issues. To address these problems, we study a new type of regulariza- tion approach that encourages the supports of weight vectors in RL models to have small overlap, by simultaneously promoting near-orthogonality among vectors and sparsity of each vector. We apply the proposed regularizer to two models: neural networks (NNs) and sparse coding (SC), and develop an efficient ADMM-based algorithm for regu- larized SC. Experiments on various datasets demonstrate that weight vectors learned under our regularizer are more interpretable and have better generalization performance.

Abstract--With the spreading prevalence of Big Data, many advances have recently been made in this field. Frameworks such as Apache Hadoop and Apache Spark have gained a lot of traction over the past decades and have become massively popular, especially in industries. It is becoming increasingly evident that effective big data analysis is key to solving artificial intelligence problems. Thus, a multi-algorithm library was implemented in the Spark framework, called MLlib. While this library supports multiple machine learning algorithms, there is still scope to use the Spark setup efficiently for highly timeintensive and computationally expensive procedures like deep learning. In this paper, we propose a novel framework that combines the distributive computational abilities of Apache Spark and the advanced machine learning architecture of a deep multilayer perceptron (MLP), using the popular concept of Cascade Learning. We conduct empirical analysis of our framework on two real world datasets. The results are encouraging and corroborate our proposed framework, in turn proving that it is an improvement over traditional big data analysis methods that use either Spark or Deep learning as individual elements. A. Overview I. INTRODUCTION With the amount of data growing at an exponential rate, it is necessary to develop tools that are able to harness that data and extract value from it.

With the increasing popularity of machine learning techniques, it has become common to see prediction algorithms operating within some larger process. However, the criteria by which we train these algorithms often differ from the ultimate criteria on which we evaluate them. This paper proposes an end-to-end approach for learning probabilistic machine learning models in a manner that directly captures the ultimate task-based objective for which they will be used, within the context of stochastic programming. We present three experimental evaluations of the proposed approach: a classical inventory stock problem, a real-world electrical grid scheduling task, and a real-world energy storage arbitrage task. We show that the proposed approach can outperform both traditional modeling and purely black-box policy optimization approaches in these applications.

Some of the biggest names in tech are lining up to join Montreal's burgeoning artificial intelligence cluster, but harnessing the sector's full potential depends on creating homegrown tech champions, not just celebrating investments by large multinationals, warns one of Canada's godfathers of deep learning. Canada is at the centre of research charting new ways to mine big data with implications for everything from better medical diagnoses to self-driving cars and Montreal is emerging as a hub thanks to a large concentration of available researchers in a low-cost city with great social values. Facebook became the latest Silicon Valley giant to set up shop in the city with a Sept. 15 announcement that it would open a research lab and invest $7 million in Montreal's AI community, joining Google, Microsoft and Samsung, which all have a presence in the city. More deals are likely on the way, according to Yoshua Bengio, considered one of the pioneers of deep learning -- an AI subset that uses neural networks to mimic the way a human brain learns and adapts. Bengio, who heads the Montreal Institute for Learning Algorithms, one of Canada's three main AI centres of excellence, recently partnered with Samsung to open a University of Montreal lab that will focus on developing algorithms for use in voice and visual recognition, robotics, autonomous driving and translations.

The 1983 movie "War Games" has a memorable climax where the supercomputer known as WOPR (War Operation Plan Response) is asked to train on itself to discover the concept of an un-winnable game. The character played by Mathew Broderick asks "Is there any way that it can play itself?" The solution is the same, set the number of players to zero (i.e. There is plenty to digest about this latest breakthrough in Deep Learning technology. DeepMind authors use the term "self-play reinforcement learning". As I remarked in the piece about "Tribes of AI", DeepMind is particularly fond of their Reinforcement Learning (RL) approach. DeepMind has taken the use of Deep Learning layers in combination with more classical RL approaches to an art form. AlphaGo Zero is the latest incarnation of its Go-playing automation.

The deep learning framework can effectively identify cracks in nuclear reactors by analyzing individual video frames.

We have written extensively about the potential of artificial intelligence for redesigning healthcare. How it could help medical professionals in designing treatment plans and finding the best-suited methods for every patient. How it could assist repetitive, monotonous tasks, so physicians and nurses can concentrate on their actual jobs instead of e.g. By what means A.I. could prioritize e-mails in doctors' inboxes or keep them up-to-date with the help of finding the latest and most relevant scientific studies in seconds. How its transformative power makes it as important as the stethoscope, the symbol of modern medicine, which appeared in the 19th century. There are already great examples for its use in several hospitals: Google DeepMind launched a partnership with the UK's National Health Service to improve the process of delivering care with digital solutions.

This is the age of artificial intelligence. Machine Learning and predictive analytics are now established and integral to just about every modern businesses, but artificial intelligence expands the scale of what's possible within those fields. It's what makes deep learning possible. Systems with greater ostensible autonomy and complexity can solve similarly complex problems. If Deep Learning is able to solve more complex problems and perform tasks of greater sophistication, building them is naturally a bigger challenge for data scientists and engineers.