Modal regression estimates the local modes of the distribution of $Y$ given $X=x$, instead of the mean, as in the usual regression sense, and can hence reveal important structure missed by usual regression methods. We study a simple nonparametric method for modal regression, based on a kernel density estimate (KDE) of the joint distribution of $Y$ and $X$. We derive asymptotic error bounds for this method, and propose techniques for constructing confidence sets and prediction sets. The latter is used to select the smoothing bandwidth of the underlying KDE. The idea behind modal regression is connected to many others, such as mixture regression and density ridge estimation, and we discuss these ties as well.

The problem of detecting communities in a graph is maybe one the most studied inference problems, given its simplicity and widespread diffusion among several disciplines. A very common benchmark for this problem is the stochastic block model or planted partition problem, where a phase transition takes place in the detection of the planted partition by changing the signal-to-noise ratio. Optimal algorithms for the detection exist which are based on spectral methods, but we show these are extremely sensible to slight modification in the generative model. Recently Javanmard, Montanari and Ricci-Tersenghi [13] have used statistical physics arguments, and numerical simulations to show that finding communities in the stochastic block model via semidefinite programming is quasi optimal. Further, the resulting semidefinite relaxation can be solved efficiently, and is very robust with respect to changes in the generative model. In this paper we study in detail several practical aspects of this new algorithm based on semidefinite programming for the detection of the planted partition.

This was a great question posted on Quora.com, and attracted many comments. Here we summarize the must interesting contributions for you.

Are there any Recurrent convolutional neural network network implementations out there? I was hoping to implement the text classifier mentioned in this paper.

Or questions about analytic acumen such as the ability to visualize patterns in time series or charts, with the naked eye? Indeed some of the best data scientists don't even code anymore, they may play with API's or design architecture and systems. Anyway, interesting test, worth trying if you are looking to get hired in a role involving coding. Below is a sample question.

The ever-increasing pace of change in today's organizations requires that executives understand and then quickly respond to constant shifts in how their businesses operate and how work must get done. That means you must resist your innate biases against doing new things in new ways, scan the horizon for growth opportunities, and push yourself to acquire drastically different capabilities--while still doing your existing job. To succeed, you must be willing to experiment and become a novice over and over again, which for most of us is an extremely discomforting proposition. Over decades of work with managers, the author has found that people who do succeed at this kind of learning have four well-developed attributes: aspiration, self-awareness, curiosity, and vulnerability. They have a deep desire to understand and master new skills; they see themselves very clearly; they're constantly thinking of and asking good questions; and they tolerate their own mistakes as they move up the curve.

"Our research shows that a growing number of customers actually prefer self-service channels to answer questions, resolve issues or complete transactions. Yet, automated handling often hits limitations when it comes to handling complex queries or'remembering' information previously mentioned in a conversation," says Dan Miller, Opus Research lead analyst. "As intelligent assistant technology evolves; we anticipate the emergence of highly specialized'intelligent advisors' that know when and how to involve a live agent. Inbenta's Hybrid Chat is the beginning of this progress." "As a transactional e-commerce-based company, having a superior digital customer support program is essential. You wouldn't make your brick and mortar customers search your store without helping them, so why not give them a personalized experience virtually," says Andreia Ferreira, Live Chat Manager, Ticketbis.

Editor's Note: Alex Meshkin is the CEO of Flow Health. Flow Health provides longitudinal care plan coordination and chronic care management services built on top of its platform, which is The Operating System for Value-Based CareSM. We have seen incredible progress in machine learning and artificial intelligence (AI) over the past few years, especially through the application of deep learning algorithms. AI systems will get even better as more data is collected, so faster data gathering and better data integration should lead to smarter and more useful AI systems. Recently I described a new class of system that I believe will take form and leverage AI and combine workflow automation to improve how care is delivered -- I termed this: "Intelligent Clinical Decision Automation."

It also means the recipients of such tales of fantasy are often thrown off the scent of the story they should be following. Those stories were followed up by one of the most breathtaking pieces of myopic'journalism' I've seen from TechCrunch in quite a while." It would be equally knee jerk to make excuses for one of the true darlings of the enterprise startup crowd, a BI vendor that is positioning itself as "the world's first business cloud." That's the Domo rabbit hole a naive tech journalist can get bamboozled in. You can call Den Howlett a lot of things, but naive tech journalist ain't one of'em. Here he resists the temptation to roast in order to weigh out the pros and cons in detail. But the key is not whether Domo screwed up their PR, but whether they are ready to backup their enterprise ambitions. Den likes the micro-service hub potential, but for now, he's got one eyebrow raised: "I challenge Domo to explain how any service can credibly be called a'business cloud' that manages everything you need without access to the financial information." Scott Cummings, one of our commenters who says he is heavily involved in enterprise sales, adds: "I have yet to meet a paying Domo customer, and those who have tried it have stated it is at best "frosting on the cake" The plot is already thick, my friends….

IBM is about to deliver the foundation of a brain-inspired supercomputer to Lawrence Livermore National Laboratory, one of the federal government's top research institutions. The delivery is one small "blade" within a server rack with 16 chips, dubbed TrueNorth, and is modeled after the way the human brain functions. Silicon Valley is awash in optimism about artificial intelligence, largely based on the progress that deep learning neural networks are making in solving big problems. Companies from Google to Nvidia are hoping they'll provide the AI smarts for self-driving cars and other tough problems. It is within this environment that IBM has been pursuing solutions in brain-inspired supercomputers. The main benefit is that such chips may be able to operate at lower frequencies and get much more work done on a much smaller amount of power.