S
Sergio Guadarrama
Researcher at Google
Publications - 71
Citations - 39193
Sergio Guadarrama is an academic researcher from Google. The author has contributed to research in topics: Fuzzy logic & Fuzzy set operations. The author has an hindex of 34, co-authored 68 publications receiving 35677 citations. Previous affiliations of Sergio Guadarrama include Technical University of Madrid & University of California, Berkeley.
Papers
More filters
Journal ArticleDOI
Fuzzy representations need a careful design
Enric Trillas,Sergio Guadarrama +1 more
TL;DR: The way in which this design of the representation is done by means of fuzzy sets, connectives and relations marks a distinction between the fuzzy and the formal logic methodologies, two different disciplines whose design process and agendas are not coincidental.
Posted Content
PixColor: Pixel Recursive Colorization
TL;DR: In this paper, the task of automated colorization is relatively easy given a low-resolution version of the color image, and a conditional PixelCNN is trained to generate a low resolution color for a given grayscale image.
Book
Multiple-valued logic and artificial intelligence fundamentals of fuzzy control revisited
TL;DR: In this article, a review of fuzzy control in Artificial Intelligence can be found, which can be traced back to multiple-valued logic (MVL) and can be classified into three categories: fuzzy control, fuzzy sets, and fuzzy connectives.
Journal Article
Large scale visual recognition through adaptation using joint representation and multiple instance learning
Judy Hoffman,Deepak Pathak,Eric Tzeng,Jonathan Long,Sergio Guadarrama,Trevor Darrell,Kate Saenko +6 more
TL;DR: This work provides a novel formulation of a joint multiple instance learning method that includes examples from object-centric data with image-level labels when available, and also performs domain transfer learning to improve the underlying detector representation.
Journal ArticleDOI
Multiple-Valued Logic and Artificial IntelligenceFundamentals of Fuzzy Control Revisited
TL;DR: This paper reviews one particular area of Artificial Intelligence, which roots may be traced back to Multiple-valued Logic: the area of fuzzy control and shows that a parameterization of either the fuzzy sets or the connectives used to express the rules governing a fuzzy controller allows the use of new optimization methods to improve the overall performance.