Reinforcement Learning by Policy Search

One objective of artificial intelligence is to model the behavior of an intelligent agent interacting with its environment. The environment's transformations can be modeled as a Markov chain, whose state is partially observable to the agent and affected by its actions; such processes are known as partially observable Markov decision processes (POMDPs). While the environment's dynamics are assumed to obey certain rules, the agent does not know them and must learn. In this dissertation we focus on the agent's adaptation as captured by the reinforcement learning framework. This means learning a policy---a mapping of observations into actions---based on feedback from the environment. The learning can be viewed as browsing a set of policies while evaluating them by trial through interaction with the environment. The set of policies is constrained by the architecture of the agent's controller. POMDPs require a controller to have a memory. We investigate controllers with memory, including controllers with external memory, finite state controllers and distributed controllers for multi-agent systems. For these various controllers we work out the details of the algorithms which learn by ascending the gradient of expected cumulative reinforcement. Building on statistical learning theory and experiment design theory, a policy evaluation algorithm is developed for the case of experience re-use. We address the question of sufficient experience for uniform convergence of policy evaluation and obtain sample complexity bounds for various estimators. Finally, we demonstrate the performance of the proposed algorithms on several domains, the most complex of which is simulated adaptive packet routing in a telecommunication network.

Learning Commonsense Categorical Knowledge in a Thread Memory System

If we are to understand how we can build machines capable of broad purpose learning and reasoning, we must first aim to build systems that can represent, acquire, and reason about the kinds of commonsense knowledge that we humans have about the world. This endeavor suggests steps such as identifying the kinds of knowledge people commonly have about the world, constructing suitable knowledge representations, and exploring the mechanisms that people use to make judgments about the everyday world. In this work, I contribute to these goals by proposing an architecture for a system that can learn commonsense knowledge about the properties and behavior of objects in the world. The architecture described here augments previous machine learning systems in four ways: (1) it relies on a seven dimensional notion of context, built from information recently given to the system, to learn and reason about objects' properties; (2) it has multiple methods that it can use to reason about objects, so that when one method fails, it can fall back on others; (3) it illustrates the usefulness of reasoning about objects by thinking about their similarity to other, better known objects, and by inferring properties of objects from the categories that they belong to; and (4) it represents an attempt to build an autonomous learner and reasoner, that sets its own goals for learning about the world and deduces new facts by reflecting on its acquired knowledge. This thesis describes this architecture, as well as a first implementation, that can learn from sentences such as ``A blue bird flew to the tree'' and ``The small bird flew to the cage'' that birds can fly. One of the main contributions of this work lies in suggesting a further set of salient ideas about how we can build broader purpose commonsense artificial learners and reasoners.

Learning Linear, Sparse, Factorial Codes

In previous work (Olshausen & Field 1996), an algorithm was described for learning linear sparse codes which, when trained on natural images, produces a set of basis functions that are spatially localized, oriented, and bandpass (i.e., wavelet-like). This note shows how the algorithm may be interpreted within a maximum-likelihood framework. Several useful insights emerge from this connection: it makes explicit the relation to statistical independence (i.e., factorial coding), it shows a formal relationship to the algorithm of Bell and Sejnowski (1995), and it suggests how to adapt parameters that were previously fixed.

Observations on Cortical Mechanisms for Object Recognition andsLearning

This paper sketches a hypothetical cortical architecture for visual 3D object recognition based on a recent computational model. The view-centered scheme relies on modules for learning from examples, such as Hyperbf-like networks. Such models capture a class of explanations we call Memory-Based Models (MBM) that contains sparse population coding, memory-based recognition, and codebooks of prototypes. Unlike the sigmoidal units of some artificial neural networks, the units of MBMs are consistent with the description of cortical neurons. We describe how an example of MBM may be realized in terms of cortical circuitry and biophysical mechanisms, consistent with psychophysical and physiological data.

Sparse Representations of Multiple Signals

We discuss the problem of finding sparse representations of a class of signals. We formalize the problem and prove it is NP-complete both in the case of a single signal and that of multiple ones. Next we develop a simple approximation method to the problem and we show experimental results using artificially generated signals. Furthermore,we use our approximation method to find sparse representations of classes of real signals, specifically of images of pedestrians. We discuss the relation between our formulation of the sparsity problem and the problem of finding representations of objects that are compact and appropriate for detection and classification.

Sparse Correlation Kernel Analysis and Reconstruction

This paper presents a new paradigm for signal reconstruction and superresolution, Correlation Kernel Analysis (CKA), that is based on the selection of a sparse set of bases from a large dictionary of class- specific basis functions. The basis functions that we use are the correlation functions of the class of signals we are analyzing. To choose the appropriate features from this large dictionary, we use Support Vector Machine (SVM) regression and compare this to traditional Principal Component Analysis (PCA) for the tasks of signal reconstruction, superresolution, and compression. The testbed we use in this paper is a set of images of pedestrians. This paper also presents results of experiments in which we use a dictionary of multiscale basis functions and then use Basis Pursuit De-Noising to obtain a sparse, multiscale approximation of a signal. The results are analyzed and we conclude that 1) when used with a sparse representation technique, the correlation function is an effective kernel for image reconstruction and superresolution, 2) for image compression, PCA and SVM have different tradeoffs, depending on the particular metric that is used to evaluate the results, 3) in sparse representation techniques, L_1 is not a good proxy for the true measure of sparsity, L_0, and 4) the L_epsilon norm may be a better error metric for image reconstruction and compression than the L_2 norm, though the exact psychophysical metric should take into account high order structure in images.

An Equivalence Between Sparse Approximation and Support Vector Machines

In the first part of this paper we show a similarity between the principle of Structural Risk Minimization Principle (SRM) (Vapnik, 1982) and the idea of Sparse Approximation, as defined in (Chen, Donoho and Saunders, 1995) and Olshausen and Field (1996). Then we focus on two specific (approximate) implementations of SRM and Sparse Approximation, which have been used to solve the problem of function approximation. For SRM we consider the Support Vector Machine technique proposed by V. Vapnik and his team at AT&T Bell Labs, and for Sparse Approximation we consider a modification of the Basis Pursuit De-Noising algorithm proposed by Chen, Donoho and Saunders (1995). We show that, under certain conditions, these two techniques are equivalent: they give the same solution and they require the solution of the same quadratic programming problem.

Memory Hierarchy Hardware-Software Co-design in Embedded Systems

The memory hierarchy is the main bottleneck in modern computer systems as the gap between the speed of the processor and the memory continues to grow larger. The situation in embedded systems is even worse. The memory hierarchy consumes a large amount of chip area and energy, which are precious resources in embedded systems. Moreover, embedded systems have multiple design objectives such as performance, energy consumption, and area, etc. Customizing the memory hierarchy for specific applications is a very important way to take full advantage of limited resources to maximize the performance. However, the traditional custom memory hierarchy design methodologies are phase-ordered. They separate the application optimization from the memory hierarchy architecture design, which tend to result in local-optimal solutions. In traditional Hardware-Software co-design methodologies, much of the work has focused on utilizing reconfigurable logic to partition the computation. However, utilizing reconfigurable logic to perform the memory hierarchy design is seldom addressed. In this paper, we propose a new framework for designing memory hierarchy for embedded systems. The framework will take advantage of the flexible reconfigurable logic to customize the memory hierarchy for specific applications. It combines the application optimization and memory hierarchy design together to obtain a global-optimal solution. Using the framework, we performed a case study to design a new software-controlled instruction memory that showed promising potential.

Memory Usage Inference for Object-Oriented Programs

We present a type-based approach to statically derive symbolic closed-form formulae that characterize the bounds of heap memory usages of programs written in object-oriented languages. Given a program with size and alias annotations, our inference system will compute the amount of memory required by the methods to execute successfully as well as the amount of memory released when methods return. The obtained analysis results are useful for networked devices with limited computational resources as well as embedded software.

Scaling algorithms for distributed max flow

Bibliography: p. 22-24.

Failure-Oblivious Computing and Boundless Memory Blocks

Memory errors are a common cause of incorrect software execution and security vulnerabilities. We have developed two new techniques that help software continue to execute successfully through memory errors: failure-oblivious computing and boundless memory blocks. The foundation of both techniques is a compiler that generates code that checks accesses via pointers to detect out of bounds accesses. Instead of terminating or throwing an exception, the generated code takes another action that keeps the program executing without memory corruption. Failure-oblivious code simply discards invalid writes and manufactures values to return for invalid reads, enabling the program to continue its normal execution path. Code that implements boundless memory blocks stores invalid writes away in a hash table to return as the values for corresponding out of bounds reads. he net effect is to (conceptually) give each allocated memory block unbounded size and to eliminate out of bounds accesses as a programming error. We have implemented both techniques and acquired several widely used open source servers (Apache, Sendmail, Pine, Mutt, and Midnight Commander).With standard compilers, all of these servers are vulnerable to buffer overflow attacks as documented at security tracking web sites. Both failure-oblivious computing and boundless memory blocks eliminate these security vulnerabilities (as well as other memory errors). Our results show that our compiler enables the servers to execute successfully through buffer overflow attacks to continue to correctly service user requests without security vulnerabilities.

Sexual orientation and spatial memory

Resumen tomado de la publicaci??n

Attention, memory and verbal learning and their relation to schizotypal traits in unaffected parents of schizophrenic patients

The main objective of this ex post facto study is to compare the differences in cognitive functions and their relation to schizotypal personality traits between a group of unaffected parents of schizophrenic patients and a control group. A total of 52 unaffected biological parents of schizophrenic patients and 52 unaffected parents of unaffected subjects were assessed in measures of attention (Continuous Performance Test- Identical Pairs Version, CPT-IP), memory and verbal learning (California Verbal Learning Test, CVLT) as well as schizotypal personality traits (Oxford-Liverpool Inventory of Feelings and Experiences, O-LIFE). The parents of the patients with schizophrenia differ from the parents of the control group in omission errors on the Continuous Performance Test- Identical Pairs, on a measure of recall and on two contrast measures of the California Verbal Learning Test. The associations between neuropsychological variables and schizotpyal traits are of a low magnitude. There is no defined pattern of the relationship between cognitive measures and schizotypal traits

El papel de la memoria de trabajo en el cálculo mental un cuarto de siglo después de Hitch = The role of working memory in mental arithmetic a quarter of century after Hitch

Desde que Hitch (1978) publicó el primer estudio sobre el rol de la memoria de trabajo en el cálculo han ido aumentando las investigaciones en este campo. Muchos trabajos han estudiado un único subsistema, pero nuestro objetivo es identificar qué subsistema de la memoria de trabajo (bucle fonológico, agenda viso-espacial o ejecutivo central) está más implicado en el cálculo mental. Para ello hemos realizado un estudio correlacional en el que hemos administrado dos pruebas aritméticas y nueve pruebas de la “Bateria de Test de Memòria de Treball” de Pickering, Baqués y Gathercole (1999) a una muestra de 94 niños españoles de 7-8 años. Nuestros resultados indican que el bucle fonológico y sobretodo el ejecutivo central inciden de forma estadísticamente significativa en el rendimiento aritmético

Short-term storage and mental speed account for the relationship between working memory and fluid intelligence. 'El almacenamiento a corto plazo y la velocidad mental dan cuenta de la relaci??n entre memoria de trabajo e inteligencia fluida'

Resumen tomado de la publicaci??n