Twitter is currently, yet again, ablaze at the mere thought coming from the one we call Musk. Elon Musk recently tweeted out, and has previously expressed, that the so-called neural lace, is a way for humanity to propel itself forward into its own evolution, and as a way to deter ourselves from becoming "obsolete" in the ever growing world of the artificial intelligence. As soon as I heard of the plans for a neural lace though, my alarm bells started chiming, because as utopian as it all may sound, I think all it will do is open up a direct channel for A.I. to invade our human brain, and in some way or another, whether positive, negative, or neutral, make use of the awesome equipment we carry in our wetware. What is this "lace" you speak of? In simple terms it is an interface between hardware, software, and wetware, marrying the human brain to digital components, so as to increase the bandwidth of human processing power, and decompress the means of person-to-person communication, although I think person-to-many would not be far behind too.

For the month of April, we also recognize the most popular posts and blogger based on unique page views (UPV) and social shares. Most Viewed and Most Shared - Platinum Badge ( 20,000 UPV AND 2,000 shares) 10 Free Must-Read Books for Machine Learning and Data Science, by Matthew Mayo Most Viewed - Gold Badges ( 10,000 UPV) Forrester vs Gartner on Data Science Platforms and Machine Learning Solutions, by Gregory Piatetsky Top 20 Recent Research Papers on Machine Learning and Deep Learning, by Thuy Pham Most Viewed - Silver Badges ( 5,000 unique PV) Awesome Deep Learning: Most Cited Deep Learning Papers, by Terry Taewoong Um 5 Machine Learning Projects You Can No Longer Overlook, April, by Matthew Mayo Keep it simple! How to understand Gradient Descent algorithm, by Jahnavi Mahanta Top mistakes data scientists make when dealing with business people, by Karolis Urbonas (new) New Online Data Science Tracks for 2017, by Brendan Martin (new) Cartoon: Machine Learning - What They Think I Do, by Harrison Kinsley Data Science for the Layman (No Math Added), Annalyn Ng and Kenneth Soo Most Shared - Gold Badges ( 1,000 shares) Forrester vs Gartner on Data Science Platforms and Machine Learning Solutions, by Gregory Piatetsky Top 20 Recent Research Papers on Machine Learning and Deep Learning, by Thuy Pham Top mistakes data scientists make when dealing with business people, by Karolis Urbonas (new) Awesome Deep Learning: Most Cited Deep Learning Papers, by Terry Taewoong Um Most Shared - Silver Gold Badges ( 500 shares) Keep it simple! How to understand Gradient Descent algorithm A Brief History of Artificial Intelligence, By Francesco Corea The 42 V's of Big Data and Data Science, by Tom Shafer (new) Deep Stubborn Networks - A Breakthrough Advance Towards Adversarial Machine Intelligence, by Matthew Mayo (new) Awesome Deep Learning: Most Cited Deep Learning Papers, by Terry Taewoong Um 5 Machine Learning Projects You Can No Longer Overlook, April, by Matthew Mayo Keep it simple! How to understand Gradient Descent algorithm A Brief History of Artificial Intelligence, By Francesco Corea The 42 V's of Big Data and Data Science, by Tom Shafer (new) Deep Stubborn Networks - A Breakthrough Advance Towards Adversarial Machine Intelligence, by Matthew Mayo (new)

Many machine learning systems are built to solve the hardest examples of a particular task, which often makes them large and expensive to run--especially with respect to the easier examples, which might require much less computation. For an agent with a limited computational budget, this "one-size-fits-all" approach may result in the agent wasting valuable computation on easy examples, while not spending enough on hard examples. Rather than learning a single, fixed policy for solving all instances of a task, we introduce a metacontroller which learns to optimize a sequence of "imagined" internal simulations over predictive models of the world in order to construct a more informed, and more economical, solution. The metacontroller component is a model-free reinforcement learning agent, which decides both how many iterations of the optimization procedure to run, as well as which model to consult on each iteration. The models (which we call "experts") can be state transition models, action-value functions, or any other mechanism that provides information useful for solving the task, and can be learned on-policy or off-policy in parallel with the metacontroller. When the metacontroller, controller, and experts were trained with "interaction networks" (Battaglia et al., 2016) as expert models, our approach was able to solve a challenging decision-making problem under complex non-linear dynamics. The metacontroller learned to adapt the amount of computation it performed to the difficulty of the task, and learned how to choose which experts to consult by factoring in both their reliability and individual computational resource costs. This allowed the metacontroller to achieve a lower overall cost (task loss plus computational cost) than more traditional fixed policy approaches. These results demonstrate that our approach is a powerful framework for using rich forward models for efficient model-based reinforcement learning. While there have been significant recent advances in deep reinforcement learning (Mnih et al., 2015; Silver et al., 2016) and control (Lillicrap et al., 2015; Levine et al., 2016), most efforts train a network that performs a fixed sequence of computations. Here we introduce an alternative in which an agent uses a metacontroller to choose which, and how many, computations to perform.

In many applications, data come with a natural ordering. This ordering can often induce local dependence among nearby variables. However, in complex data, the width of this dependence may vary, making simple assumptions such as a constant neighborhood size unrealistic. We propose a framework for learning this local dependence based on estimating the inverse of the Cholesky factor of the covariance matrix. Penalized maximum likelihood estimation of this matrix yields a simple regression interpretation for local dependence in which variables are predicted by their neighbors. Our proposed method involves solving a convex, penalized Gaussian likelihood problem with a hierarchical group lasso penalty. The problem decomposes into independent subproblems which can be solved efficiently in parallel using first-order methods. Our method yields a sparse, symmetric, positive definite estimator of the precision matrix, encoding a Gaussian graphical model. We derive theoretical results not found in existing methods attaining this structure. In particular, our conditions for signed support recovery and estimation consistency rates in multiple norms are as mild as those in a regression problem. Empirical results show our method performing favorably compared to existing methods. We apply our method to genomic data to flexibly model linkage disequilibrium. Our method is also applied to improve the performance of discriminant analysis in sound recording classification.

It is of fundamental importance to find algorithms obtaining optimal performance for learning of statistical models in distributed and communication limited systems. Aiming at characterizing the optimal strategies, we consider learning of Gaussian Processes (GPs) in distributed systems as a pivotal example. We first address a very basic problem: how many bits are required to estimate the inner-products of Gaussian vectors across distributed machines? Using information theoretic bounds, we obtain an optimal solution for the problem which is based on vector quantization. Two suboptimal and more practical schemes are also presented as substitute for the vector quantization scheme. In particular, it is shown that the performance of one of the practical schemes which is called per-symbol quantization is very close to the optimal one. Schemes provided for the inner-product calculations are incorporated into our proposed distributed learning methods for GPs. Experimental results show that with spending few bits per symbol in our communication scheme, our proposed methods outperform previous zero rate distributed GP learning schemes such as Bayesian Committee Model (BCM) and Product of experts (PoE).

Wearable computing is one of the fastest growing technologies today. Smart watches are poised to take over at least of half the wearable devices market in the near future. Smart watch screen size, however, is a limiting factor for growth, as it restricts practical text input. On the other hand, wearable devices have some features, such as consistent user interaction and hands-free, heads-up operations, which pave the way for gesture recognition methods of text entry. This paper proposes a new text input method for smart watches, which utilizes motion sensor data and machine learning approaches to detect letters written in the air by a user. This method is less computationally intensive and less expensive when compared to computer vision approaches. It is also not affected by lighting factors, which limit computer vision solutions. The AirDraw system prototype developed to test this approach is presented. Additionally, experimental results close to 71% accuracy are presented.

The paper presents a novel, principled approach to train recurrent neural networks from the Reservoir Computing family that are robust to missing part of the input features at prediction time. By building on the ensembling properties of Dropout regularization, we propose a methodology, named DropIn, which efficiently trains a neural model as a committee machine of subnetworks, each capable of predicting with a subset of the original input features. We discuss the application of the DropIn methodology in the context of Reservoir Computing models and targeting applications characterized by input sources that are unreliable or prone to be disconnected, such as in pervasive wireless sensor networks and ambient intelligence. We provide an experimental assessment using real-world data from such application domains, showing how the Dropin methodology allows to maintain predictive performances comparable to those of a model without missing features, even when 20\%-50\% of the inputs are not available.

Online reviews provide viewpoints on the strengths and shortcomings of products/services, influencing potential customers' purchasing decisions. However, the proliferation of non-credible reviews -- either fake (promoting/ demoting an item), incompetent (involving irrelevant aspects), or biased -- entails the problem of identifying credible reviews. Prior works involve classifiers harnessing rich information about items/users -- which might not be readily available in several domains -- that provide only limited interpretability as to why a review is deemed non-credible. This paper presents a novel approach to address the above issues. We utilize latent topic models leveraging review texts, item ratings, and timestamps to derive consistency features without relying on item/user histories, unavailable for "long-tail" items/users. We develop models, for computing review credibility scores to provide interpretable evidence for non-credible reviews, that are also transferable to other domains -- addressing the scarcity of labeled data. Experiments on real-world datasets demonstrate improvements over state-of-the-art baselines.

With pressure to increase graduation rates and reduce time to degree in higher education, it is important to identify at-risk students early. Automated early warning systems are therefore highly desirable. In this paper, we use unsupervised clustering techniques to predict the graduation status of declared majors in five departments at California State University Northridge (CSUN), based on a minimal number of lower division courses in each major. In addition, we use the detected clusters to identify hidden bottleneck courses.

MEDABLE Inc., a leading application and analytics platform for healthcare, announced Cerebrum, the first cloud-based machine learning solution created specifically for healthcare apps. Cerebrum leverages data gathering smartphones with a first-of-its-kind machine learning engine, resulting in health events becoming more easily predicted, such as warning an elderly relative when he is at greatest risk of a fall, or preventing an asthmatic child from triggering a life threatening episode. Smartphones are the planet's dominant accessory. Cerebrum can be used with Apple HealthKit, CareKit and other mobile platforms to more effectively learn and treat digital signatures of health and disease. Medable's analytics platform was built to address the unique concerns of the healthcare and life sciences industry, and provide artificial intelligence to the entire ecosystem.