[ { "id": "authors:1gb87-beh35", "collection": "authors", "collection_id": "1gb87-beh35", "cite_using_url": "https://resolver.caltech.edu/CaltechAUTHORS:20160229-160500915", "type": "book_section", "title": "An Integrated Vision Sensor for the Computation of Optical Flow Singular Points", "book_title": "Advances in Neural Information Processing Systems 11 (NIPS 1998)", "author": [ { "family_name": "Higgins", "given_name": "Charles M.", "clpid": "Higgins-C-M" }, { "family_name": "Koch", "given_name": "Christof", "orcid": "0000-0001-6482-8067", "clpid": "Koch-C" } ], "contributor": [ { "family_name": "Kearns", "given_name": "Michael S.", "clpid": "Kearns-M-S" }, { "family_name": "Solla", "given_name": "Sara A.", "clpid": "Solla-S-A" }, { "family_name": "Cohn", "given_name": "David A.", "clpid": "Cohn-D-A" } ], "abstract": "A robust, integrative algorithm is presented for computing the position of the focus of expansion or axis of rotation (the singular point) in optical flow fields such as those generated by self-motion. Measurements are shown of a fully parallel CMOS analog VLSI motion sensor array which\ncomputes the direction of local motion (sign of optical flow) at each pixel and can directly implement this algorithm. The flow field singular point is computed in real time with a power consumption of less than 2 mW.\nComputation of the singular point for more general flow fields requires measures of field expansion and rotation, which it is shown can also be computed in real-time hardware, again using only the sign of the optical\nflow field. These measures, along with the location of the singular point, provide robust real-time self-motion information for the visual guidance of a moving platform such as a robot.", "isbn": "0-262-11245-0", "publisher": "MIT Press", "place_of_publication": "Cambridge, MA", "publication_date": "1999", "pages": "699-705" }, { "id": "authors:4rfnf-ejn40", "collection": "authors", "collection_id": "4rfnf-ejn40", "cite_using_url": "https://resolver.caltech.edu/CaltechAUTHORS:20160203-163952250", "type": "book_section", "title": "Learning Fuzzy Rule-Based Neural Networks for Control", "book_title": "Advances in Neural Information Processing Systems 5 (NIPS 1992)", "author": [ { "family_name": "Higgins", "given_name": "Charles M.", "clpid": "Higgins-C-M" }, { "family_name": "Goodman", "given_name": "Rodney M.", "clpid": "Goodman-R-M" } ], "contributor": [ { "family_name": "Hanson", "given_name": "Stephen Jos\u00e9", "clpid": "Hanson-S-J" }, { "family_name": "Cowan", "given_name": "Jack D.", "clpid": "Cowan-J-D" }, { "family_name": "Giles", "given_name": "C. Lee", "clpid": "Giles-C-L" } ], "abstract": "A three-step method for function approximation with a fuzzy system is proposed. First, the membership functions and an initial rule representation are learned; second, the rules are compressed as much as possible using information theory; and finally, a computational network is constructed to compute the function value. This system is applied to two control examples: learning the truck and trailer backer-upper control system, and learning a cruise control\nsystem for a radio-controlled model car.", "isbn": "1-55860-274-7", "publisher": "Morgan Kaufmann", "place_of_publication": "San Mateo, CA", "publication_date": "1993", "pages": "350-357" }, { "id": "authors:4kqn3-31f69", "collection": "authors", "collection_id": "4kqn3-31f69", "cite_using_url": "https://resolver.caltech.edu/CaltechAUTHORS:20190314-155127145", "type": "book_section", "title": "Learning fuzzy rule-based neural networks for function approximation", "book_title": "[Proceedings 1992] IJCNN International Joint Conference on Neural Networks", "author": [ { "family_name": "Higgins", "given_name": "C. M.", "clpid": "Higgins-C-M" }, { "family_name": "Goodman", "given_name": "R. M.", "clpid": "Goodman-R-M" } ], "abstract": "In this paper, we present a method for the induction of fuzzy logic rules to predict a numerical function from samples of the function and its dependent variables. This method uses an information-theoretic approach based on our previous work with discrete-valued data [3]. The rules learned can then be used in a neural network to predict the function value based upon its dependent variables. An example is shown of learning a control system function.", "doi": "10.1109/ijcnn.1992.287127", "isbn": "0780305590", "publisher": "IEEE", "place_of_publication": "Piscataway, NJ", "publication_date": "1992-06", "pages": "251-256" }, { "id": "authors:11yy9-8df91", "collection": "authors", "collection_id": "11yy9-8df91", "cite_using_url": "https://resolver.caltech.edu/CaltechAUTHORS:20190314-142000764", "type": "book_section", "title": "Incremental learning with rule-based neural networks", "book_title": "IJCNN-91-Seattle International Joint Conference on Neural Networks", "author": [ { "family_name": "Higgins", "given_name": "C. M.", "clpid": "Higgins-C-M" }, { "family_name": "Goodman", "given_name": "R. M.", "clpid": "Goodman-R-M" } ], "abstract": "A classifier for discrete-valued variable classification problems is presented. The system utilizes an information-theoretic algorithm for constructing informative rules from example data. These rules are then used to construct a neural network to perform parallel inference and posterior probability estimation. The network can be grown incrementally, so that new data can be incorporated without repeating the training on previous data. It is shown that this technique performs as well as other techniques such as backpropagation while having unique advantages in incremental learning capability, training efficiency, knowledge representation, and hardware implementation suitability.", "doi": "10.1109/ijcnn.1991.155294", "isbn": "0780301641", "publisher": "IEEE", "place_of_publication": "Piscataway, NJ", "publication_date": "1991-07", "pages": "875-880" }, { "id": "authors:paqsj-wzc27", "collection": "authors", "collection_id": "paqsj-wzc27", "cite_using_url": "https://resolver.caltech.edu/CaltechAUTHORS:20190314-142001533", "type": "book_section", "title": "Incremental Rule-based Learning", "book_title": "Proceedings. 1991 IEEE International Symposium on Information Theory", "author": [ { "family_name": "Higgins", "given_name": "Charles M.", "clpid": "Higgins-C-M" }, { "family_name": "Goodman", "given_name": "Rodney M.", "clpid": "Goodman-R-M" } ], "abstract": "In a system which learns to predict the value of an output variable given one or more input variables by looking at a set of examples, a rule-based knowledge representation provides not only a natural method of constructing a classifier, but also a human-readable explanation of what has been learned. Consider a rule of the form if y then x where y is a conjunction of values of input variables and x is a value of the output variable. The number of input variables in y is called the order of the rule. In previous work, a measure of the information content or \"value\" of such a rule has been developed (the J-measure. It has been shown in [3] that a classifier can be built from the rules obtained by a constrained search of all possible rules which performs comparably with other classifiers.", "doi": "10.1109/isit.1991.695344", "isbn": "0780300564", "publisher": "IEEE", "place_of_publication": "Piscataway, NJ", "publication_date": "1991-06", "pages": "288" } ]