Browsing by Author "Uhr, Leonard"
Now showing items 8-27 of 44
-
Describing, Using "Recognition Cones"
Uhr, Leonard (University of Wisconsin-Madison Department of Computer Sciences, 1973)Parallel-serial perceptual "recognition cones" (RE-CO-DERS) are being developed to handle scenes of interacting objects, by successively transforming and coalescing information. Recognition cones apply the same mechanisms ... -
The Description of Scenes Over Time and Space
Uhr, Leonard (University of Wisconsin-Madison Department of Computer Sciences, 1973)This paper explores techniques for pattern recognition and description of more than one object, where objects extend over time as well as over space. Three major interrelated issues are examined: A. Describing, as opposed ... -
EASEy-2: An English-Like Program Language
Uhr, Leonard (University of Wisconsin-Madison Department of Computer Sciences, 1973) -
EASEy: An English-Like Programming Language for Artificial Intelligence and Complex Information Processing
Uhr, Leonard (University of Wisconsin-Madison Department of Computer Sciences, 1974)EASEy (an Encoder for Algorithmic Syntactic English that's easy)is a programming language for list-processing and pattern-matching systems of the sort typically used for artificial intelligence and complex information ... -
Experimental Results Indicate that Generation, Local Receptive Fields and Global Convergence Improve Perceptual Learning in Connectionist Networks
Honavar, Vasant; Uhr, Leonard (University of Wisconsin-Madison Department of Computer Sciences, 1988) -
Feasible Multi-Computer Architectures, Given 3-Dimensional Stacked Wafers
Uhr, Leonard (University of Wisconsin-Madison Department of Computer Sciences, 1983) -
Flexible Linguistic Pattern Recognition
Uhr, Leonard (University of Wisconsin-Madison Department of Computer Sciences, 1970) -
Flexible Pattern Recognition
Uhr, Leonard (University of Wisconsin-Madison Department of Computer Sciences, 1969)This paper presents and describes a sequence of three computer programs that examine what "flexibility" might mean in the context of pattern recognition. Flexibility is a vague, but important, concept, and it is something ... -
Flexible Pattern Recognizers are also Concept Formers
Uhr, Leonard (University of Wisconsin-Madison Department of Computer Sciences, 1973)The typical pattern recognizer (PR) applies a set of characterizers to an input. Each characterizer implies a set of possible names, and the single most highly implied name is chosen. The typical concept former (CF) applies ... -
Globally Dense (d,k) Graphs for Computer Network Architectures
Leland, Will; Quiao, Li; Uhr, Leonard (University of Wisconsin-Madison Department of Computer Sciences, 1980) -
A Higher-Level Language for a Large Parallel Array Computer
Uhr, Leonard (University of Wisconsin-Madison Department of Computer Sciences, 1979)This paper describes and discusses several pattern recognition programs that have been coded for and test-run on the CLIP parallel array computer. These programs were coded using a first version of a "higher-level language" ... -
Highly Parallel, Hierarchial, Recognition Cone Perceptual Structures
Uhr, Leonard (University of Wisconsin-Madison Department of Computer Sciences, 1987) -
A Language for Parallel Processing of Arrays, Embedded in PASCAL
Uhr, Leonard (University of Wisconsin-Madison Department of Computer Sciences, 1979) -
Layers "Recognition Cone" Networks That Pre-Process, Classify, and Describe
Uhr, Leonard (University of Wisconsin-Madison Department of Computer Sciences, 1971)This paper gives a brief overview of six types of pattern recognition programs that (1) pre-process, then characterize, (2) pre-process and characterize together, (3) pre-process and characterize into a "recognition cone", ... -
Locally versus Globally Dense Graphs for Computer Networks
Uhr, Leonard (University of Wisconsin-Madison Department of Computer Sciences, 1981) -
A Model of Form Perception and Scene Description
Uhr, Leonard (University of Wisconsin-Madison Department of Computer Sciences, 1974)This paper examines a computer-programmed model for human recognition and description of scenes of objects that extend over time as well as space. When the scene contains several objects, the model will first output a ... -
Network and Array Architectures for Real-Time Perception
Uhr, Leonard (University of Wisconsin-Madison Department of Computer Sciences, 1981) -
A Network of Neuron-Like Units That Learns to Perceive by Generation as Well as Reweighting of its Links
Honavar, Vasant; Uhr, Leonard (University of Wisconsin-Madison Department of Computer Sciences, 1988) -
On Benchmarks: Dynamically Improving Experimental Comparisons
Uhr, Leonard (University of Wisconsin-Madison Department of Computer Sciences, 1984) -
Parallel, Hierarchical Software/Hardware Pyramid Architectures
Uhr, Leonard (University of Wisconsin-Madison Department of Computer Sciences, 1986)