It's a beautiful introduction ... Try not to drool too much! Read "A Few Useful Things to Know about Machine Learning" by Prof. Pedro Domingos. It's densely packed with valuable information, but not opaque. The author understands that there's a lot of "black art" and folk wisdom, and they invite you in. Take your time with this one.

You've probably heard it before: "a bad craftsman blames his tools." But when is the last time you saw someone building a house with a hammer, a hand saw and some 2x4s? When you build a house, you need the right tools and materials to build a house. When you build a skills, there are a different set of tools and materials. The basic ingredients for learning are neurons and myelin. Each time you fire a set of neurons while learning, they get wrapped in another thin layer of myelin, which is like insulation on an electric cord.

"As our technologies change the world, the responsibility only grows deeper for each of us to take an active role in shaping it the way we want--not the other way around."-Ray It's what we teach; it's what we expect from the world and expect our students to understand. When I was a teenager growing up in a working class town, I can recall the horror stories of robots which would take over our jobs and that would make human workers redundant….literally. It turned out that the'robots' of the time were actually automated processes and machinery with little or no sign of the robots my over active imagination conjured up after years of watching sci-fi films. Jobs were not lost en masse in my little town and humans were not rendered redundant…well not by mechanical beasts anyway.

A major challenge in the training of recurrent neural networks is the so-called vanishing or exploding gradient problem. The use of a norm-preserving transition operator can address this issue, but parametrization is challenging. In this work we focus on unitary operators and describe a parametrization using the Lie algebra $\mathfrak{u}(n)$ associated with the Lie group $U(n)$ of $n \times n$ unitary matrices. The exponential map provides a correspondence between these spaces, and allows us to define a unitary matrix using $n^2$ real coefficients relative to a basis of the Lie algebra. The parametrization is closed under additive updates of these coefficients, and thus provides a simple space in which to do gradient descent. We demonstrate the effectiveness of this parametrization on the problem of learning arbitrary unitary operators, comparing to several baselines and outperforming a recently-proposed lower-dimensional parametrization. We additionally use our parametrization to generalize a recently-proposed unitary recurrent neural network to arbitrary unitary matrices, using it to solve standard long-memory tasks.

In a Harvard Business School classroom in Boston, MA, robots are on the rise. MBA students are trying to crack a case study on the self-driving cars pioneered by Tesla, Google, and Uber. What is the potential for robots to reshape our roads? And what are the challenges and opportunities of entering that business? This is a case that David Yoffie, professor of international business administration, believes is essential reading for tomorrow's business leaders.

Late one Friday night in early November, Jun Rekimoto, a distinguished professor of human-computer interaction at the University of Tokyo, was online preparing for a lecture when he began to notice some peculiar posts rolling in on social media. Apparently Google Translate, the company's popular machine-translation service, had suddenly and almost immeasurably improved. Rekimoto visited Translate himself and began to experiment with it. He had to go to sleep, but Translate refused to relax its grip on his imagination. Rekimoto wrote up his initial findings in a blog post. First, he compared a few sentences from two published versions of "The Great Gatsby," Takashi Nozaki's 1957 translation and Haruki Murakami's more recent iteration, with what this new Google Translate was able to produce. Murakami's translation is written "in very polished Japanese," Rekimoto explained to me later via email, but the prose is distinctively "Murakami-style."

Always wanted to become a Data Scientist or a Machine Learning Engineer? We have come up with a list of top online courses that we know you will surely have fun learning. These specially selected courses will help you get started with data science, machine learning, and deep mining along with learning Python and R programming. The Discounts will be available for a few days only, so make sure to take advantage of them NOW! This is not one of those fluffy classes where everything works out just the way it should and your training is smooth sailing. This course throws you into the deep end.

Yiling Chen (yiling@seas.harvard.edu) is Gordon McKay Professor of Computer Science at Harvard University, Cambridge, MA. Arpita Ghosh (arpitaghosh@cornell.edu) is an associate professor of information science at Cornell University, Ithaca, NY. Michael Kearns (mkearns@cis.upenn.edu) is a professor and National Center Chair of Computer and Information Science at the University of Pennsylvania, Philadelphia, PA. Tim Roughgarden (tim@cs.stanford.edu) is an associate professor of CS at Stanford University, Stanford, CA. Jennifer Wortman Vaughan (jenn@microsoft.com) is a senior researcher at Microsoft Research, New York, NY.

In a variety of research areas, the weighted bag of vectors and the histogram are widely used descriptors for complex objects. Both can be expressed as discrete distributions. D2-clustering pursues the minimum total within-cluster variation for a set of discrete distributions subject to the Kantorovich-Wasserstein metric. D2-clustering has a severe scalability issue, the bottleneck being the computation of a centroid distribution, called Wasserstein barycenter, that minimizes its sum of squared distances to the cluster members. In this paper, we develop a modified Bregman ADMM approach for computing the approximate discrete Wasserstein barycenter of large clusters. In the case when the support points of the barycenters are unknown and have low cardinality, our method achieves high accuracy empirically at a much reduced computational cost. The strengths and weaknesses of our method and its alternatives are examined through experiments, and we recommend scenarios for their respective usage. Moreover, we develop both serial and parallelized versions of the algorithm. By experimenting with large-scale data, we demonstrate the computational efficiency of the new methods and investigate their convergence properties and numerical stability. The clustering results obtained on several datasets in different domains are highly competitive in comparison with some widely used methods in the corresponding areas.

Here's a conversation I had recently with Cleverbot. What are your views on the future of chatbots in language learning? User: What are your views on the future of chatbots in language learning? User: Do you think there is a future for chatbots in language education? Cleverbot: Sure, if you are talking about the moon. I also tried to have a conversation with Alice, the avatar from EFL Classroom Bot, listed by Larry Ferlazzo as one of'the best online chatbots for practicing English'.