In machine learning, the one-class classification problem occurs when training instances are only available from one class. It has been observed that making use of this class's structure, or its different contexts, may improve one-class classifier performance. Although this observation has been demonstrated for static data, a rigorous application of the idea within the data stream environment is lacking. To address this gap, we propose the use of context to guide one-class classifier learning in data streams, paying particular attention to the challenges presented by the dynamic learning environment. We present three frameworks that learn contexts and conduct experiments with synthetic and benchmark data streams. We conclude that the paradigm of contexts in data streams can be used to improve the performance of streaming one-class classifiers.

Increasing the batch size is a popular way to speed up neural network training, but beyond some critical batch size, larger batch sizes yield diminishing returns. In this work, we study how the critical batch size changes based on properties of the optimization algorithm, including acceleration and preconditioning, through two different lenses: large scale experiments, and analysis of a simple noisy quadratic model (NQM). We experimentally demonstrate that optimization algorithms that employ preconditioning, specifically Adam and K-FAC, result in much larger critical batch sizes than stochastic gradient descent with momentum. We also demonstrate that the NQM captures many of the essential features of real neural network training, despite being drastically simpler to work with. The NQM predicts our results with preconditioned optimizers, previous results with accelerated gradient descent, and other results around optimal learning rates and large batch training, making it a useful tool to generate testable predictions about neural network optimization.

A key challenge in developing and deploying Machine Learning (ML) systems is understanding their performance across a wide range of inputs. To address this challenge, we created the What-If Tool, an open-source application that allows practitioners to probe, visualize, and analyze ML systems, with minimal coding. The What-If Tool lets practitioners test performance in hypothetical situations, analyze the importance of different data features, and visualize model behavior across multiple models and subsets of input data. It also lets practitioners measure systems according to multiple ML fairness metrics. We describe the design of the tool, and report on real-life usage at different organizations.

The eCornell Machine Learning Certificate Program consists of 7 two-week courses aimed at developers, software and data engineers, data scientists and statisticians. Interested parties can take a pre-test to gauge their level of knowledge.

There's a global shortage of artificial intelligence (AI) talent; labour markets all over the world can't keep up with the demand for developers, mathematicians and scientists who can create new and innovative AI technology. There are an estimated 1,600 AI startups just in Europe, not factoring in the AI initiatives in large tech companies, so the wait for new AI graduates remains long. Microsoft has recently announced the goal of training 15,000 new AI professionals by 2022, which is a good start but not enough to fill the estimated millions of roles that are currently vacant. In a recent study, Microsoft and IDC found that the shortage of workers with AI skills has stopped companies that want to adopt AI from being able to do so. Until more highly skilled AI developers enter the workforce, organisations must find creative ways to supplement the talent they need to initiate their AI projects across industries--whether those projects involve voice, image, or pattern recognition, enabling autonomous movement or simulating realistic conversations. These innovations can underpin a new generation of healthcare tools, smart home devices or digital personal assistants.

Dr. Mitchell Pryor earned is BSME at Southern Methodist University in 1993. After graduating, he taught math and science courses at St. James School in St. James Maryland before returning to Texas. He completed is Masters (1999) and PhD (2002) at UT Austin with an emphasis on the modeling, simulation, and operation of redundant manipulators. Since earning his PhD, Dr. Pryor has taught graduate and undergraduate courses in the mechanical and electrical engineering departments as well as led and conducted research in the area of robotics and automation in Mechanical Engineering, Petroleum Engineering and the Nuclear Engineering Teaching Laboratory. He has worked for numerous research sponsors including, NASA, DARPA, DOE, INL, LANL, ORNL, Y-12, and many industrial partners.

A link has been posted to your Facebook feed. Despite sending humans to Earth's orbit and the moon, the idea of humans surviving in outer space must seem like science fiction. Creating an environment that can sustain human life in the almost total absence of gravity, as well as no electrical outlets or oxygen, takes a lot of experimentation. That's been the job of teams of dedicated scientists who have facilitated some of the most unforgettable moments in space exploration. We compiled 30 common items that were invented for use in the race for space.

When quantitative models are used to support decision-making on complex and important topics, understanding a model's ``reasoning'' can increase trust in its predictions, expose hidden biases, or reduce vulnerability to adversarial attacks. However, the concept of interpretability remains loosely defined and application-specific. In this paper, we introduce a mathematical framework in which machine learning models are constructed in a sequence of interpretable steps. We show that for a variety of models, a natural choice of interpretable steps recovers standard interpretability proxies (e.g., sparsity in linear models). We then generalize these proxies to yield a parametrized family of consistent measures of model interpretability. This formal definition allows us to quantify the ``price'' of interpretability, i.e., the tradeoff with predictive accuracy. We demonstrate practical algorithms to apply our framework on real and synthetic datasets.

Traditionally, the automatic recognition of human activities is performed with supervised learning algorithms on limited sets of specific activities. This work proposes to recognize recurrent activity patterns, called routines, instead of precisely defined activities. The modeling of routines is defined as a metric learning problem, and an architecture, called SS2S, based on sequence-to-sequence models is proposed to learn a distance between time series. This approach only relies on inertial data and is thus non intrusive and preserves privacy. Experimental results show that a clustering algorithm provided with the learned distance is able to recover daily routines.

We attempt to make two arguments in this essay. First, through a case study of a mobile phone based voice-media service we have been running in rural central India for more than six years, we describe several implementation complexities we had to navigate towards realizing our intended vision of bringing social development through technology. Most of these complexities arose in the interface of our technology with society, and we argue that even other technology providers can create similar processes to manage this socio-technological interface and ensure intended outcomes from their technology use. We then build our second argument about how to ensure that the organizations behind both market driven technologies and those technologies that are adopted by the state, pay due attention towards responsibly managing the socio-technological interface of their innovations. We advocate for the technology engineers and researchers who work within these organizations, to take up the responsibility and ensure that their labour leads to making the world a better place especially for the poor and marginalized. We outline possible governance structures that can give more voice to the technology developers to push their organizations towards ensuring that responsible outcomes emerge from their technology. We note that the examples we use to build our arguments are limited to contemporary information and communication technology (ICT) platforms used directly by end-users to share content with one another, and hence our argument may not generalize to other ICTs in a straightforward manner.