Publications
-
Incorporating linguistic features in a hybrid HMM/MLP speech recognizer
We propose two schemes for incorporating distinctive speech features (sonorant, fricative, nasal, vocalic, and voiced) into the MLP component of our system. We show a small improvement in recognition performance…
-
On the direct determination of epipoles: a case study in algebraic methods for geometric problems
Studies experimentally the problem of computing the position of the epipoles in a pair of uncalibrated images; three families of methods are successively considered.
-
Automated Drawing of Metabolic Pathways
This paper presents algorithms for drawing metabolic pathways by dynamically querying the underlying knowledge base.
-
On Using Technology For Understanding Science
This essay calls for the science education community to consider seriously the educational implications of technology-derived fundamental changes in scientific methodologies.
-
The Role of Voice in Human-Machine Communication
This chapter reviews application areas in which spoken interaction may play a significant role, assesses potential benefits of spoken interaction with machines, and attempts to compare voice with alternative and…
-
Canonic representations for the geometries of multiple projective views
We show how a special decomposition of general projection matrices, called canonic enables us to build geometric descriptions for a system of cameras which are invariant with respect to a given group…
-
Greedy Attribute Selection
We examine five greedy hillclimbing procedures that search for attribute sets that generalize well with ID3/C4.5. Experiments suggest hillclimbing in attribute space can yield substantial improvements in generalization performance.
-
Hybrid Reasoning using Universal Attachment
Universal attachment is a domain-independent mechanism for integrating diverse representation and reasoning methods into hybrid frameworks that contain a subsystem based on deduction over logical formulas.
-
Representations of Metabolic Knowledge: Pathways
The chief contributions of the paper are a minimized representation for biochemical pathways called the predecessor list, and inference procedures for converting the predecessor list into a pathway-graph representation that…
-
Computing motion and structure in image sequences without calibration
This paper proposes an algebraic method to generalize the usual equations of structure from motion, when calibration is not available.
-
Representing, Analyzing, and Synthesizing Biochemical Pathways
This article describes challenges and opportunities for addressing computational problems in the metabolism with techniques from knowledge representation, planning, integration of heterogeneous databases, qualitative reasoning, knowledge acquisition, and machine learning.
-
Evidential Reasoning and Project Early Warning Systems
PEWS combines a proven project reporting methodology with the latest artificial intelligence techniques such as evidential reasoning. Together, they ensure the successful outcome of large projects.