Intelligence by Design: Principles of Modularity and Coordination for Engineerin

All intelligence relies on search --- for example, the search for an intelligent agent's next action. Search is only likely to succeed in resource-bounded agents if they have already been biased towards finding the right answer. In artificial agents, the primary source of bias is engineering. This dissertation describes an approach, Behavior-Oriented Design (BOD) for engineering complex agents. A complex agent is one that must arbitrate between potentially conflicting goals or behaviors. Behavior-oriented design builds on work in behavior-based and hybrid architectures for agents, and the object oriented approach to software engineering. The primary contributions of this dissertation are: 1.The BOD architecture: a modular architecture with each module providing specialized representations to facilitate learning. This includes one pre-specified module and representation for action selection or behavior arbitration. The specialized representation underlying BOD action selection is Parallel-rooted, Ordered, Slip-stack Hierarchical (POSH) reactive plans. 2.The BOD development process: an iterative process that alternately scales the agent's capabilities then optimizes the agent for simplicity, exploiting tradeoffs between the component representations. This ongoing process for controlling complexity not only provides bias for the behaving agent, but also facilitates its maintenance and extendibility. The secondary contributions of this dissertation include two implementations of POSH action selection, a procedure for identifying useful idioms in agent architectures and using them to distribute knowledge across agent paradigms, several examples of applying BOD idioms to established architectures, an analysis and comparison of the attributes and design trends of a large number of agent architectures, a comparison of biological (particularly mammalian) intelligence to artificial agent architectures, a novel model of primate transitive inference, and many other examples of BOD agents and BOD development.

Maximum Entropy Discrimination

We present a general framework for discriminative estimation based on the maximum entropy principle and its extensions. All calculations involve distributions over structures and/or parameters rather than specific settings and reduce to relative entropy projections. This holds even when the data is not separable within the chosen parametric class, in the context of anomaly detection rather than classification, or when the labels in the training set are uncertain or incomplete. Support vector machines are naturally subsumed under this class and we provide several extensions. We are also able to estimate exactly and efficiently discriminative distributions over tree structures of class-conditional models within this framework. Preliminary experimental results are indicative of the potential in these techniques.

Biologically Plausible Neural Circuits for Realization of Maximum Operations

Object recognition in the visual cortex is based on a hierarchical architecture, in which specialized brain regions along the ventral pathway extract object features of increasing levels of complexity, accompanied by greater invariance in stimulus size, position, and orientation. Recent theoretical studies postulate a non-linear pooling function, such as the maximum (MAX) operation could be fundamental in achieving such invariance. In this paper, we are concerned with neurally plausible mechanisms that may be involved in realizing the MAX operation. Four canonical circuits are proposed, each based on neural mechanisms that have been previously discussed in the context of cortical processing. Through simulations and mathematical analysis, we examine the relative performance and robustness of these mechanisms. We derive experimentally verifiable predictions for each circuit and discuss their respective physiological considerations.

Notes on PCA, Regularization, Sparsity and Support Vector Machines

We derive a new representation for a function as a linear combination of local correlation kernels at optimal sparse locations and discuss its relation to PCA, regularization, sparsity principles and Support Vector Machines. We first review previous results for the approximation of a function from discrete data (Girosi, 1998) in the context of Vapnik"s feature space and dual representation (Vapnik, 1995). We apply them to show 1) that a standard regularization functional with a stabilizer defined in terms of the correlation function induces a regression function in the span of the feature space of classical Principal Components and 2) that there exist a dual representations of the regression function in terms of a regularization network with a kernel equal to a generalized correlation function. We then describe the main observation of the paper: the dual representation in terms of the correlation function can be sparsified using the Support Vector Machines (Vapnik, 1982) technique and this operation is equivalent to sparsify a large dictionary of basis functions adapted to the task, using a variation of Basis Pursuit De-Noising (Chen, Donoho and Saunders, 1995; see also related work by Donahue and Geiger, 1994; Olshausen and Field, 1995; Lewicki and Sejnowski, 1998). In addition to extending the close relations between regularization, Support Vector Machines and sparsity, our work also illuminates and formalizes the LFA concept of Penev and Atick (1996). We discuss the relation between our results, which are about regression, and the different problem of pattern classification.

An Assessment of the Degree of Implementation of the Lean Aerospace Initiative Principles and Practices within the US Aerospace and Defense Industry

This report is a formal documentation of the results of an assessment of the degree to which Lean Principles and Practices have been implemented in the US Aerospace and Defense Industry. An Industry Association team prepared it for the DCMA-DCAAIndustry Association “Crosstalk” Coalition in response to a “Crosstalk” meeting action request to the industry associations. The motivation of this request was provided by the many potential benefits to system product quality, affordability and industry responsiveness, which a high degree of industry Lean implementation can produce.

Discrete and continuous compositions

This paper examines a dataset which is modeled well by the Poisson-Log Normal process and by this process mixed with Log Normal data, which are both turned into compositions. This generates compositional data that has zeros without any need for conditional models or assuming that there is missing or censored data that needs adjustment. It also enables us to model dependence on covariates and within the composition

Compositional analysis of bivariate discrete probabilities

A joint distribution of two discrete random variables with finite support can be displayed as a two way table of probabilities adding to one. Assume that this table has n rows and m columns and all probabilities are non-null. This kind of table can be seen as an element in the simplex of n · m parts. In this context, the marginals are identified as compositional amalgams, conditionals (rows or columns) as subcompositions. Also, simplicial perturbation appears as Bayes theorem. However, the Euclidean elements of the Aitchison geometry of the simplex can also be translated into the table of probabilities: subspaces, orthogonal projections, distances. Two important questions are addressed: a) given a table of probabilities, which is the nearest independent table to the initial one? b) which is the largest orthogonal projection of a row onto a column? or, equivalently, which is the information in a row explained by a column, thus explaining the interaction? To answer these questions three orthogonal decompositions are presented: (1) by columns and a row-wise geometric marginal, (2) by rows and a columnwise geometric marginal, (3) by independent two-way tables and fully dependent tables representing row-column interaction. An important result is that the nearest independent table is the product of the two (row and column)-wise geometric marginal tables. A corollary is that, in an independent table, the geometric marginals conform with the traditional (arithmetic) marginals. These decompositions can be compared with standard log-linear models. Key words: balance, compositional data, simplex, Aitchison geometry, composition, orthonormal basis, arithmetic and geometric marginals, amalgam, dependence measure, contingency table

The ISSA Pedagogical Standards: a tool to influence quality in early childhood programs

The ISSA Pedagogical Standards were first published in 2001 as a network-developed tool that defined quality in teaching practices and the classroom environment and captured the changes that had occurred in the region since 1994 when the Step by Step Program, an initiative to promote democratic principles in early childhood development and education, was launched. The Program was built on belief that each child has the right to receive maximum support for the development of his or her full potential, and this work should be done in partnership and close cooperation with families, communities and professionals

Discrete Dynamical Systems

Exercises and solutions for a third or fourth year maths course. Diagrams for the questions are all together in the support.zip file, as .eps files

Programming Principles: Starting Out

In this lecture we describe the structure of the Programming Principles course at Southampton, look at the definitions and paradigms of programming, and take a look ahead to the key things that we will be covering in the weeks ahead.

Programming Principles: Introduction to Java

In this lecture we look at key concepts in Java: how to write, compile and run Java programs, define a simple class, create a main method, and use if/else structures to define behaviour.

Programming Principles: Variables, Primitives, Objects and Scope

In this session we look more closely at the way that Java deals with variables, and in particular with the differences between primitives (basic types like int and char) and objects. We also take an initial look at the scoping rules in Java, which dictate the visibility of variables in your program

Programming Principles: Computational Thinking

In this session we look at how to think systematically about a problem and create a solution. We look at the definition and characteristics of an algorithm, and see how through modularisation and decomposition we can then choose a set of methods to create. We also compare this somewhat procedural approach, with the way that design works in Object Oriented Systems,

Programming Principles: Methods

In this session we look at how to create more powerful objects through more powerful methods. We look at parameters and call by value vs. call by reference; return types; and overloading.

Programming Principles: Encapsulation and Constructors

In this session we look at the public and protected keywords, and the principle of encapsulation. We also look at how Constructors can help you initialise objects, while maintaining the encapsulation principle.