Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

According to W. Edwards Deming, American companies require nothing less than a transformation of management style and of governmental relations with industry. In Out of the Crisis, originally published in 1982, Deming offers a theory of management based on his famous 14 Points for Management. Management's failure to plan for the future, he claims, brings about loss of market, which brings about loss of jobs. Management must be judged not only by the quarterly dividend, but by innovative plans to stay in business, protect investment, ensure future dividends, and provide more jobs through improved product and service. In simple, direct language, he explains the principles of management transformation and how to apply them.

Out of the Crisis

The concept of an agent has become important in both Artificial Intelligence (AI) and mainstream computer science. Our aim in this paper is to point the reader at what we perceive to be the most important theoretical and practical issues associated with the design and construction of intelligent agents. For convenience, we divide these issues into three areas (though as the reader will see, the divisions are at times somewhat arbitrary). Agent theory is concerned with the question of what an agent is, and the use of mathematical formalisms for representing and reasoning about the properties of agents. Agent architectures can be thought of as software engineering models of agents;researchers in this area are primarily concerned with the problem of designing software or hardware systems that will satisfy the properties specified by agent theorists. Finally, agent languages are software systems for programming and experimenting with agents; these languages may embody principles proposed by theorists. The paper is not intended to serve as a tutorial introduction to all the issues mentioned; we hope instead simply to identify the most important issues, and point to work that elaborates on them. The article includes a short review of current and potential applications of agent technology.

/pdf/intelligent-agents-theory-and-practice-5dchj7p8pc.pdf

Intelligent Agents: Theory and Practice

物件導向軟體之架構(Object-Oriented Software Construction)探討

From the Publisher: 
The accessible presentation of this book gives both a general view of the entire computer vision enterprise and also offers sufficient detail to be able to build useful applications. Users learn techniques that have proven to be useful by first-hand experience and a wide range of mathematical methods. A CD-ROM with every copy of the text contains source code for programming practice, color images, and illustrative movies. Comprehensive and up-to-date, this book includes essential topics that either reflect practical significance or are of theoretical importance. Topics are discussed in substantial and increasing depth. Application surveys describe numerous important application areas such as image based rendering and digital libraries. Many important algorithms broken down and illustrated in pseudo code. Appropriate for use by engineers as a comprehensive reference to the computer vision enterprise.

Computer vision : a modern approach = 计算机视觉 : 一种现代的方法

We consider the problem of specifying data structures with complex sharing in a manner that is both declarative and results in provably correct code. In our approach, abstract data types are specified using relational algebra and functional dependencies; a novel fuse operation on relational indexes specifies where the underlying physical data structure representation has sharing. We permit the user to specify different concrete shared representations for relations, and show that the semantics of the relational specification are preserved.

/pdf/data-structure-fusion-1dizcufhh1.pdf

Data structure fusion

Software systems often exhibit a surprising flexibility in the range of execution paths they can take to produce an acceptable result. This flexibility enables new techniques that augment systems with the ability to productively tolerate a wide range of errors. We show how to exploit this flexibility to obtain transformations that improve reliability and robustness or trade off accuracy in return for increased performance or decreased power consumption. We discuss how to use empirical, probabilistic, and statistical reasoning to understand why these techniques work.

/pdf/obtaining-and-reasoning-about-good-enough-software-2b3yceu5fo.pdf

Obtaining and reasoning about good enough software

This paper describes a novel approach to high-level synthesis of complex pipelined circuits, including pipelined circuits with feedback. This approach combines a high-level, modular specification language with an efficient implementation. In our system, the designer specifies the circuit as a set of independent modules connected by conceptually unbounded queues. Our synthesis algorithm automatically transforms this modular, asynchronous specification into a tightly coupled, fully synchronous implementation in synthesizable Verilog.

High-level specification and efficient implementation of pipelined circuits

We present the first verification that a neural network produces a correct output within a specified tolerance for every input of interest. We define correctness relative to a specification which identifies 1) a state space consisting of all relevant states of the world and 2) an observation process that produces neural network inputs from the states of the world. Tiling the state and input spaces with a finite number of tiles, obtaining ground truth bounds from the state tiles and network output bounds from the input tiles, then comparing the ground truth and network output bounds delivers an upper bound on the network output error for any input of interest. Results from a case study highlight the ability of our technique to deliver tight error bounds for all inputs of interest and show how the error bounds vary over the state and input spaces.

/pdf/correctness-verification-of-neural-networks-uwqsj965qz.pdf

Correctness Verification of Neural Networks.

Graceful performance degradation during overload conditions is the primary objective of soft real-time systems. Utility accrual soft real-time scheduling algorithms allow specification of highly customized temporal system behavior during overload. Such algorithms are typically found in real-time supervisory systems where significant run-time uncertainty exists. This paper outlines an investigation of several utility accrual scheduling algorithms implemented in a Real-Time Java (RTJ) environment. These alternate schedulers are constructed, tested, and evaluated under the MIT FLEX/RTJ Compiler Infrastructure. The scheduling framework for this environment and its associated scheduling primitives are described and the corresponding performance characteristics are profiled. Furthermore, we outline the architecture of an experimental distributed Real-time Java scheduler.

/pdf/utilitiy-accrual-scheduling-with-real-time-java-431e3mmts4.pdf

Martin Rinard

Papers

Data structure fusion

Obtaining and reasoning about good enough software

High-level specification and efficient implementation of pipelined circuits

Correctness Verification of Neural Networks.

Utilitiy accrual scheduling with Real-Time Java