Sam was a brilliant scientist and engineer whose work deeply influenced the fields of artificial intelligence, machine learning, applied mathematics, neural computation, and observational science. He was also a strong advocate for the use of machine learning and computational statistics for scientific data analysis and discovery. Sam T. Roweis was born on April 27, 1972. He graduated from secondary school as valedictorian of the University of Toronto Schools in 1990, and obtained a bachelor's degree with honours from the University of Toronto Engineering Science Program four years later. His first exposure to AI and neural computation occured when--as an exceptional undergraduate--he took the graduate-level Neural Network course taught by Geoffrey Hinton.

This is a tutorial aimed at trying to build up the intuition behind solution procedures for partially observable Markov decision processes (POMDPs). It sacrifices completeness for clarity. It tries to present the main problems geometrically, rather than with a series of formulas. In fact, we avoid the actual formulas altogether, try to keep notation to a minimum and rely on pictures to build up the intuition.

The course will give the student the basic ideas and intuition behind modern machine learning methods as well as a bit more formal understanding of how, why, and when they work. The underlying theme in the course is statistical inference as it provides the foundation for most of the methods covered.

In the near future, the package that you ordered online may be deposited at your doorstep by a drone: Last December, online retailer Amazon announced plans to explore drone-based delivery, suggesting that fleets of flying robots might serve as autonomous messengers that shuttle packages to customers within 30 minutes of an order. To ensure safe, timely, and accurate delivery, drones would need to deal with a degree of uncertainty in responding to factors such as high winds, sensor measurement errors, or drops in fuel. But such "what-if" planning typically requires massive computation, which can be difficult to perform on the fly. Now MIT researchers have come up with a two-pronged approach that significantly reduces the computation associated with lengthy delivery missions. The team first developed an algorithm that enables a drone to monitor aspects of its "health" in real time.

The class will cover models at the level of syntactic, semantic and discourse processing. The emphasis will be on corpus-based methods and algorithms, such as Hidden Markov Models and probabilistic context free grammars. We will discuss the use of these methods and models in a variety of applications including syntactic parsing, information extraction, statistical machine translation, and summarization. File decompression software, such as Winzip or StuffIt, is required to open the .gz Postscript viewer software, such as Ghostscript/Ghostview, can be used to view the .ps

Using humanoid robots to study human behavior.

Humans are not only adept in recognizing what class an input instance belongs to (i.e., classification task), but perhaps more remarkably, they can imagine (i.e., generate) plausible instances of a desired class with ease, when prompted. Inspired by this, we propose a framework which allows transforming Cascade-Correlation Neural Networks (CCNNs) into probabilistic generative models, thereby enabling CCNNs to generate samples from a category of interest. CCNNs are a well-known class of deterministic, discriminative NNs, which autonomously construct their topology, and have been successful in giving accounts for a variety of psychological phenomena. Our proposed framework is based on a Markov Chain Monte Carlo (MCMC) method, called the Metropolis-adjusted Langevin algorithm, which capitalizes on the gradient information of the target distribution to direct its explorations towards regions of high probability, thereby achieving good mixing properties. Through extensive simulations, we demonstrate the efficacy of our proposed framework.

There's never any shortage of buzzwords in the IT world, but when it comes to A.I., they can be hard to tell apart. Here are five things you need to understand. Artificial intelligence refers to "a broad set of methods, algorithms and technologies that make software'smart' in a way that may seem human-like to an outside observer," said Lynne Parker, director of the division of Information and Intelligent Systems for the National Science Foundation. Machine learning, computer vision, natural language processing, robotics and related topics are all part of A.I., in other words. "Some people may come up with distinctions between the two, but there is not a universal view that the two terms mean anything different," Parker said.

Discrete-time hidden Markov models are a broadly useful class of latent-variable models with applications in areas such as speech recognition, bioinformatics, and climate data analysis. It is common in practice to introduce temporal non-homogeneity into such models by making the transition probabilities dependent on time-varying exogenous input variables via a multinomial logistic parametrization. We extend such models to introduce additional non-homogeneity into the emission distribution using a generalized linear model (GLM), with data augmentation for sampling-based inference. However, the presence of the logistic function in the state transition model significantly complicates parameter inference for the overall model, particularly in a Bayesian context. To address this we extend the recently-proposed Polya-Gamma data augmentation approach to handle non-homogeneous hidden Markov models (NHMMs), allowing the development of an efficient Markov chain Monte Carlo (MCMC) sampling scheme. We apply our model and inference scheme to 30 years of daily rainfall in India, leading to a number of insights into rainfall-related phenomena in the region. Our proposed approach allows for fully Bayesian analysis of relatively complex NHMMs on a scale that was not possible with previous methods. Software implementing the methods described in the paper is available via the R package NHMM.