the complementary issue of designing classification algorithms that can deal with more complex outputs, such as trees, sequences, or sets. More generally, we consider problems involving multiple dependent output variables, structured output spaces, and classification problems with class attributes. In order

Learning general functional dependencies is one of the main goals in machine learning. Recent progress in kernel-based methods has focused on designing flexible and powerful input representations. This paper addresses the complementary issue of problems involving complex outputs suchas multiple

This paper addresses the problem of improving the accuracy of an hypothesis output by a learning algorithm in the distribution-free (PAC) learning model. A concept class is learnable (or strongly learnable) if, given access to a Source of examples of the unknown concept, the learner with high

, creating a multi-layer structure. Once a new hidden unit has been added to the network, its input-side weights are frozen. This unit then becomes a permanent feature-detector in the network, available for producing outputs or for creating other, more complex feature detectors. The Cascade

), and difficult to optimize (which is necessary to combat the exponential complexity of verification algorithms). In this paper, we describe an integrated collection of program analysis and transformation components, called Bandera, that enables the automatic extraction of safe, compact finite-state models from

Iterative decoding of two-dimensional systematic convolutional codes has been termed “turbo” (de)coding. Using log-likelihood algebra, we show that any decoder can he used which accepts soft inputs-including a priori values-and delivers soft outputs that can he split into three terms: the soft

pixels along each line of sight. When n input images are preprocessed to create a single LDI, the size of the representation grows linearly only with the observed depth complexity in the n images, instead of linearly with n. Moreover, because the LDI data are represented in a single image coordinate

multiuser information data in a convolutionally coded asynchronous multipath DS-CDMA system. The receiver performs two successive softoutput decisions, achieved by a soft-input soft-output (SISO) multiuser detector and a bank of single-user SISO channel decoders, through an iterative process. At each

. We provide some new necessary and sufficient conditions which guarantee arbitrary pole placement of a particular linear system over the complex numbers. We exhibit a non-trivial real linear system which is not controllable by real static output feedback and discuss a conjecture from algebraic

that if simple first in first out (FIFO) input queues are used to hold packets then, even under benign conditions, head-of-line (HOL) blocking limits the achievable bandwidth to approximately 58.6 % of the maximum. HOL blocking can be overcome by the use of virtual output queueing, which is described