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

Manifold regularization is a technique that penalizes the complexity of learned functions over the intrinsic geometry of input data. We develop a connection to learning functions which are "locally stable", and propose new regularization terms for training deep neural networks that are stable against a class of local perturbations. These regularizers enable us to train a network to state-of-the-art robust accuracy of 70% on CIFAR-10 against a PGD adversary using $\ell_\infty$ perturbations of size $\epsilon = 8/255$. Furthermore, our techniques do not rely on the construction of any adversarial examples, thus running orders of magnitude faster than standard algorithms for adversarial training.

Manifold Regularization for Adversarial Robustness

Programmable analog devices have emerged as a powerful computing substrate for performing complex neuromorphic and cytomorphic computations. We present Arco, a new solver that, given a dynamical system specification in the form of a set of differential equations, generates physically realizable configurations for programmable analog devices that are algebraically equivalent to the specified system. On a set of benchmarks from the biological domain, Arco generates configurations with 35 to 534 connections and 28 to 326 components in 1 to 54 minutes.

https://dl.acm.org/doi/pdf/10.1145/2908080.2908116

Configuration synthesis for programmable analog devices with Arco

This paper introduces design-driven compilation, an approach in which the compiler uses design information to drive its analysis and verify that the program conforms to its design. Although this approach requires the programmer to specify additional design information, it offers a range of benefits, including guaranteed fidelity to the designer's expectations of the code, early and automatic detection of design nonconformance bugs, and support for local analysis, separate compilation, and libraries. It can also simplify the compiler and improve its efficiency. The key to the success of our approach is to combine high-level design specifications with powerful static analysis algorithms that handle the low-level details of verifying the design information.

/pdf/design-driven-compilation-27w9385dqt.pdf

Design-Driven Compilation

underStandInG hOw tO get a computer to perform a given task is a central question in computer science. For many years the standard answer has been to use a programming language to write a program the computer will then execute to accomplish the task. An intriguing alternative, however, is to provide the computer with examples of inputs and corresponding outputs, then have the computer automatically generalize the examples to produce a program that performs the desired task for all inputs. Researchers have worked on this approach for decades, first in the LISP community, 4 then later in the inductive logic programming community, 1–3 to name two prominent examples. Given the relatively modest size of the programs the resulting techniques are able to produce, the field has evolved to focus largely on data mining, concept learning , knowledge discovery, and other applications (as opposed to mainstream software development). The following paper focuses on an important emerging area—end user programming. As information technology has come to permeate our society, broader classes of users have developed the need for more sophisticated data manipulation and processing. While users in the past were satisfied with relatively simple interactive models of computation such as spreadsheets and other business applications, current users are now looking to automate custom data manipulations such as reformatting, reorganizing, simple calculations, or data cleaning. While such users may have a good command of the interactive functionality of their application, they often lack the expertise, time, or inclination to develop software specifically for their task. The authors illustrate how to apply example-driven program synthesis to automate spreadsheet computations. This work, therefore, is of interest to the millions of people worldwide who use spreadsheets. The methodology consists of four basic steps: ˲ Domain-specific language: Develop a domain-specific language capable of representing the desired set of computations. ˲ Data structure: Develop a data structure that can efficiently represent the large set of programs that are consistent with a given input/output example. ˲ Learn and intersect: Generate data structures for representing the programs consistent with each individual input/output example, then intersect the data structures to obtain a representation of the programs consistent with all examples. ˲ Rank the resulting set of programs , preferring more general programs over less general programs. Users can then view the results of the ranked programs on different inputs to guide the program selection process. This approach effectively addresses many of …

Example-driven program synthesis for end-user programming: technical perspective

We consider a usage model for automated machine learning (AutoML) in which users can influence the generated pipeline by providing a weak pipeline specification: an unordered set of API components from which the AutoML system draws the components it places into the generated pipeline. Such specifications allow users to express preferences over the components that appear in the pipeline, for example a desire for interpretable components to appear in the pipeline. We present AMS, an approach to automatically strengthen weak specifications to include unspecified complementary and functionally related API components, populate the space of hyperparameters and their values, and pair this configuration with a search procedure to produce a strong pipeline specification: a full description of the search space for candidate pipelines. ams uses normalized pointwise mutual information on a code corpus to identify complementary components, BM25 as a lexical similarity score over the target API's documentation to identify functionally related components, and frequency distributions in the code corpus to extract key hyperparameters and values. We show that strengthened specifications can produce pipelines that outperform the pipelines generated from the initial weak specification and an expert-annotated variant, while producing pipelines that still reflect the user preferences captured in the original weak specification.

https://dl.acm.org/doi/pdf/10.1145/3368089.3409700

Martin Rinard

Papers

Manifold Regularization for Adversarial Robustness

Configuration synthesis for programmable analog devices with Arco

Design-Driven Compilation

Example-driven program synthesis for end-user programming: technical perspective

AMS: generating AutoML search spaces from weak specifications