Archives for 2008

Today I read a paper titled “Associative Memory For Reversible Programming and Charge Recovery”

The abstract is:
Presented below is an interesting type of associative memory called toggle memory based on the concept of T flip flops, as opposed to D flip flops.

Toggle memory supports both reversible programming and charge recovery.

Circuits designed using the principles delineated below permit matchlines to charge and discharge with near zero energy dissipation.

The resulting lethargy is compensated by the massive parallelism of associative memory.

Simulation indicates over 33x reduction in energy dissipation using a sinusoidal power supply at 2 MHz, assuming realistic 50 nm MOSFET models.

Today I read a paper titled “Curve Tracking Control for Legged Locomotion in Horizontal Plane”

The abstract is:
We derive a hybrid feedback control law for the lateral leg spring (LLS) model so that the center of mass of a legged runner follows a curved path in horizontal plane.

The control law enables the runner to change the placement and the elasticity of its legs to move in a desired direction.

Stable motion along a curved path is achieved using curvature, bearing and relative distance between the runner and the curve as feedback.

Constraints on leg parameters determine the class of curves that can be followed.

We also derive an optimal control law that stabilizes the orientation of the runner’s body relative to the velocity of the runner’s center of mass.

Today I read a paper titled “Fitness inheritance in the Bayesian optimization algorithm”

The abstract is:
This paper describes how fitness inheritance can be used to estimate fitness for a proportion of newly sampled candidate solutions in the Bayesian optimization algorithm (BOA).

The goal of estimating fitness for some candidate solutions is to reduce the number of fitness evaluations for problems where fitness evaluation is expensive.

Bayesian networks used in BOA to model promising solutions and generate the new ones are extended to allow not only for modeling and sampling candidate solutions, but also for estimating their fitness.

The results indicate that fitness inheritance is a promising concept in BOA, because population-sizing requirements for building appropriate models of promising solutions lead to good fitness estimates even if only a small proportion of candidate solutions is evaluated using the actual fitness function.

This can lead to a reduction of the number of actual fitness evaluations by a factor of 30 or more.

Today I read a paper titled “Very fast watermarking by reversible contrast mapping”

The abstract is:
Reversible contrast mapping (RCM) is a simple integer transform that applies to pairs of pixels.

For some pairs of pixels, RCM is invertible, even if the least significant bits (LSBs) of the transformed pixels are lost.

The data space occupied by the LSBs is suitable for data hiding.

The embedded information bit-rates of the proposed spatial domain reversible watermarking scheme are close to the highest bit-rates reported so far.

The scheme does not need additional data compression, and, in terms of mathematical complexity, it appears to be the lowest complexity one proposed up to now.

A very fast lookup table implementation is proposed.

Robustness against cropping can be ensured as well.

Today I read a paper titled “Three-Dimensional Face Orientation and Gaze Detection from a Single Image”

The abstract is:
Gaze detection and head orientation are an important part of many advanced human-machine interaction applications.

Many systems have been proposed for gaze detection.

Typically, they require some form of user cooperation and calibration.

Additionally, they may require multiple cameras and/or restricted head positions.

We present a new approach for inference of both face orientation and gaze direction from a single image with no restrictions on the head position.

Our algorithm is based on a face and eye model, deduced from anthropometric data.

This approach allows us to use a single camera and requires no cooperation from the user.

Using a single image avoids the complexities associated with of a multi-camera system.

Evaluation tests show that our system is accurate, fast and can be used in a variety of applications, including ones where the user is unaware of the system.

Today I read a paper titled “Graphics Turing Test”

The abstract is:
We define a Graphics Turing Test to measure graphics performance in a similar manner to the definition of the traditional Turing Test.

To pass the test one needs to reach a computational scale, the Graphics Turing Scale, for which Computer Generated Imagery becomes comparatively indistinguishable from real images while also being interactive.

We derive an estimate for this computational scale which, although large, is within reach of todays supercomputers.

We consider advantages and disadvantages of various computer systems designed to pass the Graphics Turing Test.

Finally we discuss commercial applications from the creation of such a system, in particular Interactive Cinema.

Today I read a paper titled “Novelty Detection for Robot Neotaxis”

The abstract is:
The ability of a robot to detect and respond to changes in its environment is potentially very useful, as it draws attention to new and potentially important features.

We describe an algorithm for learning to filter out previously experienced stimuli to allow further concentration on novel features.

The algorithm uses a model of habituation, a biological process which causes a decrement in response with repeated presentation.

Experiments with a mobile robot are presented in which the robot detects the most novel stimulus and turns towards it (`neotaxis’).

Today I read a paper titled “Postponing Branching Decisions”

The abstract is:
Solution techniques for Constraint Satisfaction and Optimisation Problems often make use of backtrack search methods, exploiting variable and value ordering heuristics.

In this paper, we propose and analyse a very simple method to apply in case the value ordering heuristic produces ties: postponing the branching decision.

To this end, we group together values in a tie, branch on this sub-domain, and defer the decision among them to lower levels of the search tree.

We show theoretically and experimentally that this simple modification can dramatically improve the efficiency of the search strategy.

Although in practise similar methods may have been applied already, to our knowledge, no empirical or theoretical study has been proposed in the literature to identify when and to what extent this strategy should be used.

Today I read a paper titled “Implementation of float-float operators on graphics hardware”

The abstract is:
The Graphic Processing Unit (GPU) has evolved into a powerful and flexible processor.

The latest graphic processors provide fully programmable vertex and pixel processing units that support vector operations up to single floating-point precision.

This computational power is now being used for general-purpose computations.

However, some applications require higher precision than single precision.

This paper describes the emulation of a 44-bit floating-point number format and its corresponding operations.

An implementation is presented along with performance and accuracy results.

Today I read a paper titled “Dependency Parsing with Dynamic Bayesian Network”

The abstract is:
Exact parsing with finite state automata is deemed inappropriate because of the unbounded non-locality languages overwhelmingly exhibit.

We propose a way to structure the parsing task in order to make it amenable to local classification methods.

This allows us to build a Dynamic Bayesian Network which uncovers the syntactic dependency structure of English sentences.

Experiments with the Wall Street Journal demonstrate that the model successfully learns from labeled data.

Today I read a paper titled “Rule-based Knowledge Representation for Service Level Agreement”

The abstract is:
Automated management and monitoring of service contracts like Service Level Agreements (SLAs) or higher-level policies is vital for efficient and reliable distributed service-oriented architectures (SOA) with high quality of ser-vice (QoS) levels.

IT service provider need to manage, execute and maintain thousands of SLAs for different customers and different types of services, which needs new levels of flexibility and automation not available with the current technol-ogy.

I propose a novel rule-based knowledge representation (KR) for SLA rules and a respective rule-based service level management (RBSLM) framework.

My rule-based approach based on logic programming provides several advantages including automated rule chaining allowing for compact knowledge representation and high levels of automation as well as flexibility to adapt to rapidly changing business requirements.

Therewith, I address an urgent need service-oriented busi-nesses do have nowadays which is to dynamically change their business and contractual logic in order to adapt to rapidly changing business environments and to overcome the restricting nature of slow change cycles.

Today I read a paper titled “On Measuring the Impact of Human Actions in the Machine Learning of a Board Game’s Playing Policies”

The abstract is:
We investigate systematically the impact of human intervention in the training of computer players in a strategy board game.

In that game, computer players utilise reinforcement learning with neural networks for evolving their playing strategies and demonstrate a slow learning speed.

Human intervention can significantly enhance learning performance, but carry-ing it out systematically seems to be more of a problem of an integrated game development environment as opposed to automatic evolutionary learning.

Today I read a paper titled “Structural Health Monitoring Using Neural Network Based Vibrational System Identification”

The abstract is:
Composite fabrication technologies now provide the means for producing high-strength, low-weight panels, plates, spars and other structural components which use embedded fiber optic sensors and piezoelectric transducers.

These materials, often referred to as smart structures, make it possible to sense internal characteristics, such as delaminations or structural degradation.

In this effort we use neural network based techniques for modeling and analyzing dynamic structural information for recognizing structural defects.

This yields an adaptable system which gives a measure of structural integrity for composite structures.

Today I read a paper titled “A Leaf Recognition Algorithm for Plant Classification Using Probabilistic Neural Network”

The abstract is:
In this paper, we employ Probabilistic Neural Network (PNN) with image and data processing techniques to implement a general purpose automated leaf recognition algorithm.

12 leaf features are extracted and orthogonalized into 5 principal variables which consist the input vector of the PNN.

The PNN is trained by 1800 leaves to classify 32 kinds of plants with an accuracy greater than 90%.

Compared with other approaches, our algorithm is an accurate artificial intelligence approach which is fast in execution and easy in implementation.

Today I read a paper titled “Asynchronous Distributed Searchlight Scheduling”

The abstract is:
This paper develops and compares two simple asynchronous distributed searchlight scheduling algorithms for multiple robotic agents in nonconvex polygonal environments.

A searchlight is a ray emitted by an agent which cannot penetrate the boundary of the environment.

A point is detected by a searchlight if and only if the point is on the ray at some instant.

Targets are points which can move continuously with unbounded speed.

The objective of the proposed algorithms is for the agents to coordinate the slewing (rotation about a point) of their searchlights in a distributed manner, i.e., using only local sensing and limited communication, such that any target will necessarily be detected in finite time.

The first algorithm we develop, called the DOWSS (Distributed One Way Sweep Strategy), is a distributed version of a known algorithm described originally in 1990 by Sugihara et al \cite{KS-IS-MY:90}, but it can be very slow in clearing the entire environment because only one searchlight may slew at a time.

In an effort to reduce the time to clear the environment, we develop a second algorithm, called the PTSS (Parallel Tree Sweep Strategy), in which searchlights sweep in parallel if guards are placed according to an environment partition belonging to a class we call PTSS partitions.

Finally, we discuss how DOWSS and PTSS could be combined with with deployment, or extended to environments with holes.

Today I read a paper titled “On Planning while Learning”

The abstract is:
This paper introduces a framework for Planning while Learning where an agent is given a goal to achieve in an environment whose behavior is only partially known to the agent.

We discuss the tractability of various plan-design processes.

We show that for a large natural class of Planning while Learning systems, a plan can be presented and verified in a reasonable time.

However, coming up algorithmically with a plan, even for simple classes of systems is apparently intractable.

We emphasize the role of off-line plan-design processes, and show that, in most natural cases, the verification (projection) part can be carried out in an efficient algorithmic manner..

Today I read a paper titled “Population Sizing for Genetic Programming Based Upon Decision Making”

The abstract is:
This paper derives a population sizing relationship for genetic programming (GP).

Following the population-sizing derivation for genetic algorithms in Goldberg, Deb, and Clark (1992), it considers building block decision making as a key facet.

The analysis yields a GP-unique relationship because it has to account for bloat and for the fact that GP solutions often use subsolution multiple times.

The population-sizing relationship depends upon tree size, solution complexity, problem difficulty and building block expression probability.

The relationship is used to analyze and empirically investigate population sizing for three model GP problems named ORDER, ON-OFF and LOUD.

These problems exhibit bloat to differing extents and differ in whether their solutions require the use of a building block multiple times.