Google and its competitors have created a new class of large-scale computer systems to support Internet search. These “Data-Intensive Super Computing ” (DISC) systems differ from conventional supercomputers in their focus on data: they acquire and maintain continually changing data sets, in addition to performing large-scale computations over the data. With the massive amounts of data arising from such diverse sources as telescope imagery, medical records, online transaction records, and web pages, DISC systems have the potential to achieve major advances in science, health care, business efficiencies, and information access. DISC opens up many important research topics in system design, resource management, programming models, parallel algorithms, and applications. By engaging the academic research community in these issues, we can more systematically and in a more open forum explore fundamental aspects of a societally important style of computing. Keywords: parallel computing, data storage, web searchWhen a teenage boy wants to find information about his idol by using Google with the search query “Britney Spears, ” he unleashes the power of several hundred processors operating on a data set of over 200 terabytes. Why then can’t a scientist seeking a cure for cancer invoke large amounts of computation over a terabyte-sized database of DNA microarray data at the click of a button? Recent papers on parallel programming by researchers at Google [13] and Microsoft [19] present the results of using up to 1800 processors to perform computations accessing up to 10 terabytes of data. How can university researchers demonstrate the credibility of their work without having comparable computing facilities available? 1

We consider the problem of zero-shot learning, where the goal is to learn a classifier f: X → Y that must predict novel values of Y that were omitted from the training set. To achieve this, we define the notion of a semantic output code classifier (SOC) which utilizes a knowledge base of semantic properties of Y to extrapolate to novel classes. We provide a formalism for this type of classifier and study its theoretical properties in a PAC framework, showing conditions under which the classifier can accurately predict novel classes. As a case study, we build a SOC classifier for a neural decoding task and show that it can often predict words that people are thinking about from functional magnetic resonance images (fMRI) of their neural activity, even without training examples for those words. 1

Interpreting brain image experiments requires analysis of complex, multivariate data. In recent years, one analysis approach that has grown in popularity is the use of machine learning algorithms to train classifiers to decode stimuli, mental states, behaviors and other variables of interest from fMRI data and thereby show the data contain enough information about them. In this tutorial overview we review some of the key choices faced in using this approach as well as how to derive statistically significant results, illustrating each point from a case study. Furthermore, we show how, in addition to answering the question of ‘is there information about a variable of interest ’ (pattern discrimination), classifiers can be used to tackle other classes of question, namely ‘where is the information ’ (pattern localization) and ‘how is that information encoded ’ (pattern characterization). 1

In machine learning problems with tens of thousands of features and only dozens or hundreds of independent training examples, dimensionality reduction is essential for good learning performance. In previous work, many researchers have treated the learning problem in two separate phases: first use an algorithm such as singular value decomposition to reduce the dimensionality of the data set, and then use a classification algorithm such as naïve Bayes or support vector machines to learn a classifier. We demonstrate that it is possible to combine the two goals of dimensionality reduction and classification into a single learning objective, and present a novel and efficient algorithm which optimizes this objective directly. We present experimental results in fMRI analysis which show that we can achieve better learning performance and lower-dimensional representations than two-phase approaches can. 1.

Previous studies have succeeded in identifying the cognitive state corresponding to the perception of a set of depicted categories, such as tools, by analyzing the accompanying pattern of brain activity, measured with fMRI. The current research focused on identifying the cognitive state associated with a 4s viewing of an individual line drawing (1 of 10 familiar objects, 5 tools and 5 dwellings, such as a hammer or a castle). Here we demonstrate the ability to reliably (1) identify which of the 10 drawings a participant was viewing, based on that participant’s characteristic whole-brain neural activation patterns, excluding

The task of learning models for many real-world problems requires incorporating domain knowledge into learning algorithms, to enable accurate learning from a realistic volume of training data.

Functional Magnetic Resonance Imaging (fMRI) has enabled scientists to look into the active human brain. FMRI provides a sequence of 3D brain images with intensities representing brain activations. Standard techniques for fMRI analysis traditionally focused on finding the area of most significant brain activation for different sensations or activities. In this paper, we explore a new application of machine learning methods to a more challenging problem: classifying subjects into groups based on the observed 3D brain images when the subjects are performing the same task. Here we address the separation of drug-addicted subjects from healthy non-drug-using controls. In this paper, we explore a number of classification approaches. We introduce a novel algorithm that integrates side information into the use of boosting. Our algorithm clearly outperformed wellestablished classifiers as documented in extensive experimental results. This is the first time that machine learning techniques based on 3D brain images are applied to a clinical diagnosis that currently is only performed through patient self-report. Our tools can therefore provide information not addressed by traditional analysis methods and substantially improve diagnosis. 1 1.

We consider the problem of detecting the instantaneous cognitive state of a human subject based on their observed functional Magnetic Resonance Imaging (fMRI) data. Whereas fMRI has been widely used to determine average activation in different brain regions, our problem of automatically decoding instantaneous cognitive states has received little attention. This problem is relevant to diagnosing cognitive processes in neurologically normal and abnormal subjects. We describe a machine learning approach to this problem, and report on its successful use for discriminating cognitive states such as "observing a picture" versus "reading a sentence," and "reading a word about people" versus "reading a word about buildings." 1.

We introduce Hidden Process Models (HPMs), a class of probabilistic models for multivariate time series data. The design of HPMs has been motivated by the challenges of modeling hidden cognitive processes in the brain, given functional Magnetic Resonance Imaging (fMRI) data. fMRI data is sparse, high-dimensional, non-Markovian, and often involves prior knowledge of the form “hidden event A occurs n times within the interval [t,t ′]. ” HPMs provide a generalization of the widely used General Linear Model approaches to fMRI analysis, and HPMs can also be viewed as a subclass of Dynamic Bayes Networks.

implied, of any sponsoring institution, the U.S. government or any other entity.