Giorgio Vassallo

A conversational agent based on a conceptual interpretation of a data driven semantic space

In this work we propose an interpretation of the LSA framework which leads to a data-driven “conceptual” space creation suitable for an “intuitive” conversational agent. The proposed approach allows overcoming the limitations of traditional, rule-based, chat-bots, leading to a more natural dialogue.

An embedded, FPGA-based computer graphics coprocessor with native geometric algebra support

The representation of geometric objects and their transformation are the two key aspects in computer graphics applications. Traditionally, computer-intensive matrix calculations are involved in modeling and rendering three-dimensional (3D) scenery. Geometric algebra (aka Clifford algebra) is attracting attention as a natural way to model geometric facts and as a powerful analytical tool for symbolic calculations. In this paper, the architecture of Clifford coprocessor (CliffoSor) is introduced. CliffoSor is an embedded parallel coprocessing core that offers direct hardware support to Clifford algebra operators. A prototype implementation on a programmable gate array (FPGA) board is detailed. Initial test results show the potential to achieve a 20x speedup for 3D vector rotations, a 12x speedup for Clifford sums and differences, and more than a 4x speedup for Clifford products, compared to the analogous operations in GAIGEN, a standard geometric algebra library generator for general-purpose processors. An execution analysis of a raytracing application is also presented.

A Sliced Coprocessor for Native Clifford Algebra Operations

Computer graphics applications require efficient tools to model geometric objects. The traditional approach based on compute-intensive matrix calculations is error-prone due to a lack of integration between geometric reasoning and matrix-based algorithms. Clifford algebra offers a solution to these issues since it permits specification of geometry at a coordinate-free level. The best way to exploit the symbolic computing power of geometric (Clifford) algebra is supporting its data types and operators directly in hardware. This paper outlines the architecture of S-CliffoSor (Sliced Clifford coprocessor), a parallelizable embedded coprocessor that executes native Clifford algebra operations. S-CliffoSor is a sliced coprocessor that can be replicated for parallel execution of concurrent Clifford operations. A single slice has been designed, implemented and tested on the Celoxica Inc. RC1000 board. The experimental results show the potential to achieve a 3times speedup for Clifford sums and 4times speedup for Clifford products compared to against the analogous operations in the software library generator GAIGEN.

CliffoSor: a parallel embedded architecture for geometric algebra and computer graphics

Geometric object representation and their transformations are the two key aspects in computer graphics applications. Traditionally, compute-intensive matrix calculations are involved to model and render 3D scenery. Geometric algebra (a.k.a. Clifford algebra) is gaining growing attention for its natural way to model geometric facts coupled with its being a powerful analytical tool for symbolic calculations. In this paper, the architecture of CliffoSor (Clifford Processor) is introduced. ClifforSor is an embedded parallel coprocessing core that offers direct hardware support to Clifford algebra operators. A prototype implementation on an FPGA board is detailed. Initial test results show more than 4/spl times/ speedup for Clifford products against the analogous operations in GAIGEN, a standard geometric algebra library generator for general purpose processors.

Using the Hermite Regression Formula to Design a Neural Architecture with Automatic Learning of the Hidden Activation Functions

The value of the output function gradient of a neural network, calculated in the training points, plays an essential role for its generalization capability. In this paper a feed forward neural architecture (αNet) that can learn the activation function of its hidden units during the training phase is presented. The automatic learning is obtained through the joint use of the Hermite regression formula and the CGD optimization algorithm with the Powell restart conditions. This technique leads to a smooth output function of αNet in the nearby of the training points, achieving an improvement of the generalization capability and the flexibility of the neural architecture. Experimental results, obtained comparing αNet with traditional architectures with sigmoidal or sinusoidal activation functions, show that the former is very flexible and has good approximation and classification capabilities.

TSVD as a Statistical Estimator in the Latent Semantic Analysis Paradigm

The aim of this paper is to present a new point of view that makes it possible to give a statistical interpretation of the traditional latent semantic analysis (LSA) paradigm based on the truncated singular value decomposition (TSVD) technique. We show how the TSVD can be interpreted as a statistical estimator derived from the LSA co-occurrence relationship matrix by mapping probability distributions on Riemanian manifolds. Besides, the quality of the estimator model can be expressed by introducing a figure of merit arising from the Solomonoff approach. This figure of merit takes into account both the adherence to the sample data and the simplicity of the model. In our model, the simplicity parameter of the proposed figure of merit depends on the number of the singular values retained after the truncation process, while the TSVD estimator, according to the Hellinger distance, guarantees the minimal distance between the sample probability distribution and the inferred probabilistic model.

Design and Implementation of an Embedded Coprocessor with Native Support for 5D, Quadruple-Based Clifford Algebra

Geometric or Clifford algebra (CA) is a powerful mathematical tool that offers a natural and intuitive way to model geometric facts in a number of research fields, such as robotics, machine vision, and computer graphics. Operating in higher dimensional spaces, its practical use is hindered, however, by a significant computational cost, only partially addressed by dedicated software libraries and hardware/software codesigns. For low-dimensional algebras, several dedicated hardware accelerators and coprocessing architectures have been already proposed in the literature. This paper introduces the architecture of CliffordALU5, an embedded coprocessing core conceived for native execution of up to 5D CA operations. CliffordALU5 exploits a novel, hardware-oriented representation of the algebra elements that allows for faster execution of Clifford operations. In this paper, a prototype implementation of a complete system-on-chip (SOC) based on CliffordALU5 is presented. This prototype integrates an embedded processing soft-core based on the PowerPC 405 and a CliffordALU5 coprocessor on a Xilinx XUPV2P Field Programmable Gate Array (FPGA) board. Test results show a 5× average speedup for 4D Clifford products and a 4× average speedup for 5D Clifford products against the same operations in Gaigen 2, a CA software library generator running on the general-purpose PowerPC processor. This paper also presents an execution analysis of three different applications in three diverse domains, namely, inverse kinematics of a robot, optical motion capture, and raytracing, showing an average speedup between 3× and 4× with respect to the baseline Gaigen 2 implementation. Finally, a multicore approach to higher dimensional CA based on CliffordALU5 is discussed.

ConformalALU: A Conformal Geometric Algebra Coprocessor for Medical Image Processing

Medical imaging involves important computational geometric problems, such as image segmentation and analysis, shape approximation, three-dimensional (3D) modeling, and registration of volumetric data. In the last few years, Conformal Geometric Algebra (CGA), based on five-dimensional (5D) Clifford Algebra, is emerging as a new paradigm that offers simple and universal operators for the representation and solution of complex geometric problems. However, the widespread use of CGA has been so far hindered by its high dimensionality and computational complexity. This paper proposes a simplified formulation of the conformal geometric operations (reflections, rotations, translations, and uniform scaling) aimed at a parallel hardware implementation. A specialized coprocessing architecture (ConformalALU) that offers direct hardware support to the new CGA operators, is also presented. The ConformalALU has been prototyped as a complete System-on-Programmable-Chip (SoPC) on the Xilinx ML507 FPGA board, containing a Virtex-5 FPGA device. Experimental results show average speedups of one order of magnitude for CGA rotations, translations, and dilations with respect to the geometric algebra software library Gaigen running on the general-purpose PowerPC processor embedded in the target FPGA device. A suite of medical imaging applications, including segmentation, 3D modeling and registration of medical data, has been used as testbench to evaluate the coprocessor effectiveness.

Chatbots as Interface to Ontologies

Chatbots are simple conversational agents using “pattern matching rules” to carry out the dialogue with the user and various expedients to improve their credibility. However, the rules on which they are based on are too restrictive and their language understanding capability is very limited. Nevertheless chatbots are widespread in several applications, especially to provide information to users in a new and enjoyable way. In this chapter we describe different chatbot architectures, exploiting the use of ontologies in order to create clever information suppliers overcoming the main limits of chatbots: the knowledge base building and the rigidness of the dialogue mechanism.

An FPGA Implementation of a Quadruple-Based Multiplier for 4D Clifford Algebra

Geometric or Clifford algebra is an interesting paradigm for geometric modeling in fields as computer graphics, machine vision and robotics. In these areas the research effort is actually aimed at finding an efficient implementation of geometric algebra. The best way to exploit the symbolic computing power of geometric algebra is to support its data types and operators directly in hardware. However the natural representation of the algebra elements as variable-length objects causes some problems in the case of a hardware implementation. This paper proposes a 4D Clifford algebra in which the variable-length elements are mapped into fixed-length elements (quadruples). This choice leads to a simpler and more compact hardware implementation of 4D geometric algebra. The paper also presents the architecture of CliffArchy, a coprocessing core supporting the new fixed-length Clifford operands. A prototype implementation on a FPGA board is described.