Exploring Synergies between Machine Learning and Knowledge Representation to Capture Scientific Knowledge
نویسندگان
چکیده
In this paper we explore synergies between the machine learning and knowledge representation fields by considering how scientific knowledge is represented in these areas. We illustrate some of the knowledge obtained through machine learning methods, providing two contrasting examples of such models: probabilistic graphical models (aka Bayesian networks) and artificial neural networks (including deep learning networks). From knowledge representation, we give an overview of ontological representations, qualitative reasoning, and planning. Then we discuss potential synergies that would benefit both areas.
منابع مشابه
Image Classification via Sparse Representation and Subspace Alignment
Image representation is a crucial problem in image processing where there exist many low-level representations of image, i.e., SIFT, HOG and so on. But there is a missing link across low-level and high-level semantic representations. In fact, traditional machine learning approaches, e.g., non-negative matrix factorization, sparse representation and principle component analysis are employed to d...
متن کاملConcept Mapping and Expert Systems: Exploring Synergies
Concept maps and expert systems are both in the soft toolbar of knowledge modelling. We have spent nearly two decades developing our expert system shell “Doctus”. Several years ago we have seen the first concept mapping solutions and started using them very soon. Frequently we have found ourselves using both tools in a particular research or consultancy project and started to wander how the two...
متن کاملA Knowledge Media Approach Using Associative Representation for Constructing Information Bases
In this paper, we present a new approach based on knowledge medium using associative representation as a framework of information representation to gather raw information from vast information sources and to integrate it into information bases cost-e ectively. We then present a knowledge media information base system called CM-2 which provides users with a means of accumulating, sharing, explor...
متن کاملLearned parametrized dynamic movement primitives with shared synergies for controlling robotic and musculoskeletal systems
A salient feature of human motor skill learning is the ability to exploit similarities across related tasks. In biological motor control, it has been hypothesized that muscle synergies, coherent activations of groups of muscles, allow for exploiting shared knowledge. Recent studies have shown that a rich set of complex motor skills can be generated by a combination of a small number of muscle s...
متن کاملHybridization in Question Answering Systems
Question answering systems can benefit from the incorporation of a broad range of technologies, including natural language processing, machine learning, information retrieval, knowledge representation, and automated reasoning. We have designed an architecture that identifies the essential roles of components in a question answering system. This architecture greatly facilitates experimentation b...
متن کامل