In 2017, over half of senior artificial intelligence (AI) professionals stated that a lack of qualified personnel in their field is the single biggest barrier to AI implementation across businesses. As more and more companies choose to explore AI, deep learning and machine learning (ML), this knowledge gap begins to cause some serious problems. The solution may be in de-humanising ML functions by using automatic (also known as augmented or assisted) ML techniques. AI experts are costly, with a reported average annual salary of $314,000. But before you can even worry about affording an AI expert, you have to find one.

One of the interesting changes in terminology is that of the meaning of machine learning (ML). In the olden days, way back in the 1980s, machine learning referred almost exclusively to the to artificial intelligence tools of expert systems and deep learning (DL). Today, with the massive increase in computer performance, many algorithms used in business intelligence can discover many things about data and have been combined with the older techniques under an expanded definition of ML. To understand why the added complexity involved in training and deploying DL systems is useful in certain circumstances, this article describes the basics of optimization and explains what DL adds to business understanding. Optimization is mathematical speak for finding the maximum or minimum value of some function. For instance, one of the most discussed concepts in business is that of maximizing profit.

THE TERM'ARTIFICIAL INTELLIGENCE" was coined in 1956, at a historic conference at Dartmouth, but it has been only in the past 10 years, for the most part, that we've seen the first truly substantive glimpses of its power and application. A.I., as it's now universally called, is the pursuit of performing tasks usually reserved for human cognition: recognizing patterns, predicting outcomes clouded by uncertainty, and making complex decisions. A.I. algorithms can perceive and interpret the world around us--and some even say they'll soon be capable of emotion, compassion, and creativity--though the original dream of matching overall "human intelligence" is still very far away. What changed everything a decade or so ago was an approach called "deep learning"--an architecture inspired by the human brain, with neurons and connections. As the name suggests, deep-learning networks can be thousands of layers deep and have up to billions of parameters.

Event extraction is of practical utility in natural language processing. In the real world, it is a common phenomenon that multiple events existing in the same sentence, where extracting them are more difficult than extracting a single event. Previous works on modeling the associations between events by sequential modeling methods suffer a lot from the low efficiency in capturing very long-range dependencies. In this paper, we propose a novel Jointly Multiple Events Extraction (JMEE) framework to jointly extract multiple event triggers and arguments by introducing syntactic shortcut arcs to enhance information flow and attention-based graph convolution networks to model graph information. The experiment results demonstrate that our proposed framework achieves competitive results compared with state-of-the-art methods.

Spiking neural networks (SNNs) have garnered a great amount of interest for supervised and unsupervised learning applications. This paper deals with the problem of training multilayer feedforward SNNs. The non-linear integrate-and-fire dynamics employed by spiking neurons make it difficult to train SNNs to output desired spike train in response to a given input. To tackle this, first the problem of training a multilayer SNN is formulated as an optimization problem such that its objective function is based on the deviation in membrane potential rather than the spike arrival instants. Then, an optimization method named Normalized Approximate Descent (NormAD), hand-crafted for such non-convex optimization problems, is employed to derive the iterative synaptic weight update rule. Next it is reformulated for a more efficient implementation, which can also be interpreted to be spatio-temporal error backpropagation. The learning rule is validated by employing it to solve generic spike based training problem as well as a spike based formulation of the XOR problem. Thus, the new algorithm is a key step towards building deep spiking neural networks capable of event-triggered learning.

A study on power market price forecasting by deep learning is presented. As one of the most successful deep learning frameworks, the LSTM (Long short-term memory) neural network is utilized. The hourly prices data from the New England and PJM day-ahead markets are used in this study. First, a LSTM network is formulated and trained. Then the raw input and output data are preprocessed by unit scaling, and the trained network is tested on the real price data under different input lengths, forecasting horizons and data sizes. Its performance is also compared with other existing methods. The forecasted results demonstrate that, the LSTM deep neural network can outperform the others under different application settings in this problem.

Since the inception of Deep Reinforcement Learning (DRL) algorithms, there has been a growing interest in both research and industrial communities in the promising potentials of this paradigm. The list of current and envisioned applications of deep RL ranges from autonomous navigation and robotics to control applications in the critical infrastructure, air traffic control, defense technologies, and cybersecurity. While the landscape of opportunities and the advantages of deep RL algorithms are justifiably vast, the security risks and issues in such algorithms remain largely unexplored. To facilitate and motivate further research on these critical challenges, this paper presents a foundational treatment of the security problem in DRL. We formulate the security requirements of DRL, and provide a high-level threat model through the classification and identification of vulnerabilities, attack vectors, and adversarial capabilities. Furthermore, we present a review of current literature on security of deep RL from both offensive and defensive perspectives. Lastly, we enumerate critical research venues and open problems in mitigation and prevention of intentional attacks against deep RL as a roadmap for further research in this area.

Measuring similarities between unlabeled time series trajectories is an important problem in domains as diverse as medicine, astronomy, finance, and computer vision. It is often unclear what is the appropriate metric to use because of the complex nature of noise in the trajectories (e.g. different sampling rates or outliers). Domain experts typically hand-craft or manually select a specific metric, such as dynamic time warping (DTW), to apply on their data. In this paper, we propose Autowarp, an end-to-end algorithm that optimizes and learns a good metric given unlabeled trajectories. We define a flexible and differentiable family of warping metrics, which encompasses common metrics such as DTW, Euclidean, and edit distance. Autowarp then leverages the representation power of sequence autoencoders to optimize for a member of this warping distance family. The output is a metric which is easy to interpret and can be robustly learned from relatively few trajectories. In systematic experiments across different domains, we show that Autowarp often outperforms hand-crafted trajectory similarity metrics.

Near-future large galaxy surveys will encounter blended galaxy images at a fraction of up to 50% in the densest regions of the universe. Current deblending techniques may segment the foreground galaxy while leaving missing pixel intensities in the background galaxy flux. The problem is compounded by the diffuse nature of galaxies in their outer regions, making segmentation significantly more difficult than in traditional object segmentation applications. We propose a novel branched generative adversarial network (GAN) to deblend overlapping galaxies, where the two branches produce images of the two deblended galaxies. We show that generative models are a powerful engine for deblending given their innate ability to infill missing pixel values occluded by the superposition. We maintain high peak signal-to-noise ratio and structural similarity scores with respect to ground truth images upon deblending. Our model also predicts near-instantaneously, making it a natural choice for the immense quantities of data soon to be created by large surveys such as LSST, Euclid and WFIRST.

Given the sizes of modern data sets, there is a growing preference towards simple estimators that have a small computational footprint and are easy to implement. Additionally, beyond efficiency and tractability considerations, there is mounting evidence that many simple and popular estimation methods perform a kind of implicit regularization, meaning that they appear to produce estimates exhibiting a kind of regularity, even though they do not employ an explicit regularizer. Research interest in implicit regularization is growing, but the foundations of the idea date back at least 30 years in machine learning, where early-stopped gradient descent was found to be effective in training neural networks (Morgan and Bourlard, 1989), and at least 40 years in applied mathematics, where the same idea (here known as Landweber iteration) was found to help in ill-posed linear inverse problems (Strand, 1974). After a wave of work on boosting with early stopping (Buhlmann and Yu, 2003; Rosset et al., 2004; Zhang and Yu, 2005; Yao et al., 2007), more recent work focuses on the regularity properties of particular algorithms for underdetermined problems in matrix factorization, regression, and classification (Gunasekar et al., 2017; Wilson et al., 2017; Gunasekar et al., 2018). More broadly, algorithmic regularization plays a key role in training deep neural networks, via batch normalization, dropout, weight decay, and other techniques (Goodfellow et al., 2016). In this paper, we focus on early stopping in gradient descent, when applied specifically to least squares regression. This is a basic problem and we are of course not the only authors to consider it; there is now a large literature on this topic (see references above, and more to come when we discuss related work shortly). However, our perspective differs from existing work in two ways. First, we study gradient descent in continuous-time, i.e., we study gradient descent with infinitesimal step sizes, leading to a path of iterates called gradient flow; and second, we focus on the regularity 1 properties along the entire path, not just its convergence point (as is the focus in most work on implicit regularization).