Supervised machine learning models boast remarkable predictive capabilities. But can you trust your model? Will it work in deployment? What else can it tell you about the world? We want models to be not only good, but interpretable. And yet the task of interpretation appears underspecified. Papers provide diverse and sometimes non-overlapping motivations for interpretability, and offer myriad notions of what attributes render models interpretable. Despite this ambiguity, many papers proclaim interpretability axiomatically, absent further explanation. In this paper, we seek to refine the discourse on interpretability. First, we examine the motivations underlying interest in interpretability, finding them to be diverse and occasionally discordant. Then, we address model properties and techniques thought to confer interpretability, identifying transparency to humans and post-hoc explanations as competing notions. Throughout, we discuss the feasibility and desirability of different notions, and question the oft-made assertions that linear models are interpretable and that deep neural networks are not.

I'm a software engineer by training and I've had little interaction with AI. I had always wanted to delve deeper into machine learning, but never really found my "in". That's why when Google open sourced TensorFlow in November 2015, I got super excited and knew it was time to jump in and start the learning journey. Not to sound dramatic, but to me, it actually felt kind of like Prometheus handing down fire to mankind from the Mount Olympus of machine learning. In the back of my head was the idea that the entire field of Big Data and technologies like Hadoop were vastly accelerated when Google researchers released their Map Reduce paper.

This tutorial introduces a new and powerful set of techniques variously called "neural machine translation" or "neural sequence-to-sequence models". These techniques have been used in a number of tasks regarding the handling of human language, and can be a powerful tool in the toolbox of anyone who wants to model sequential data of some sort. The tutorial assumes that the reader knows the basics of math and programming, but does not assume any particular experience with neural networks or natural language processing. It attempts to explain the intuition behind the various methods covered, then delves into them with enough mathematical detail to understand them concretely, and culiminates with a suggestion for an implementation exercise, where readers can test that they understood the content in practice.

A multi-way factor analysis model is introduced for tensor-variate data of any order. Each data item is represented as a (sparse) sum of Kruskal decompositions, a Kruskal-factor analysis (KFA). KFA is nonparametric and can infer both the tensor-rank of each dictionary atom and the number of dictionary atoms. The model is adapted for online learning, which allows dictionary learning on large data sets. After KFA is introduced, the model is extended to a deep convolutional tensor-factor analysis, supervised by a Bayesian SVM. The experiments section demonstrates the improvement of KFA over vectorized approaches (e.g., BPFA), tensor decompositions, and convolutional neural networks (CNN) in multi-way denoising, blind inpainting, and image classification. The improvement in PSNR for the inpainting results over other methods exceeds 1dB in several cases and we achieve state of the art results on Caltech101 image classification.

Artificial Intelligence (AI) is on the rise. Life with smart machines is rapidly affecting the way we live and work. A visual signal is the number of companies mentioning it. Kevin Jones, a cancer researcher, describes his work as "taking a bath in uncertainty and unknowns and exceptions and outliers." Dr. Jones suggests the two most important values, given the level of uncertainty in his line of work, are humility and curiosity.

For most of us, building a chatbot serves a real business purpose and isn't just an amusing project. Since a chatbot is meant to serve or interact with customers in some way, it should be given as much information and intelligence as possible to properly interface with customers. The sooner this data is learned by the chatbot, the better -- and it's best when it is done before the chatbot even goes live. A customer-facing chatbot naturally lends itself to using information from customer support tickets. Support tickets are a treasure trove illuminating the types of concerns and issues that customers already have, and they can inform your decisions on what features to build into the chatbot and anticipate what kind of questions your chatbot should be able to answer. Since these are actual, concrete data points, you don't run the risk of imagining problems and solutions unrelated to your customers.

A few years back, a prospective doctoral student sought out Sylvia Serfaty with some existential questions about the apparent uselessness of pure math. Serfaty, then newly decorated with the prestigious Henri Poincaré Prize, won him over simply by being honest and nice. "She was very warm and understanding and human," said Thomas Leblé, now an instructor at the Courant Institute of Mathematical Sciences at New York University. "She made me feel that even if at times it might seem futile, at least it would be friendly. The intellectual and human adventure would be worth it."

Schedule and Syllabus Unless otherwise specified the course lectures and meeting times are: Wednesday, Friday 3:30-4:20 Location: 200-219 This syllabus is subject to change according to the pace of the class.

Upskilling is hard and even though this is the case, the last few years have seen a big increase in the number of people teaching themselves to code, or brushing up on their data science skills, in order to better position themselves and their companies for the future. Managers and employees in almost every industry, and even the Prime Minister, has recognised that to keep pace with a rapidly evolving world, they need to develop new skills tailored to emerging technologies. So what are the skills really needed in the next few years? Artificial Intelligence (AI) can give meaning to data patterns in minutes; humans can take days. Already big in corporate firms, the harnessing of AI to cut down on tasks is growing in popularity and is already a part of daily life for many people.