Towards Knowledge-based Generative Learning Objects
نویسندگان
چکیده
Today there are many efforts to shift the reuse dimension from component-based to generative reuse in the learning object (LO) domain. This requires more precise LO models and commonality-variability analysis. We propose a new knowledge-based model for representing LO instances. The model is based on factoring and aggregating knowledge units within a LO and is presented as a structure of interface and functionality. Interface serves for explicit describing knowledge communication to and from the LO. Functionality describes knowledge representation and managing. The model contributes to better compositionality, reusability and can be further generalized easily to support the personalized content delivery and automatic generation. Using the introduced model as a basis for generalization, we extended the known concept of generative LOs by linking domain commonality-variability analysis with meta-programming techniques for generating LO instances on demand from the generic LO specification.
منابع مشابه
Galileo: Perceiving Physical Object Properties by Integrating a Physics Engine with Deep Learning
Humans demonstrate remarkable abilities to predict physical events in dynamic scenes, and to infer the physical properties of objects from static images. We propose a generative model for solving these problems of physical scene understanding from real-world videos and images. At the core of our generative model is a 3D physics engine, operating on an object-based representation of physical pro...
متن کاملActively Learning what makes a Discrete Sequence Valid
Deep learning techniques have been hugely successful for traditional supervised and unsupervised machine learning problems. In large part, these techniques solve continuous optimization problems. Recently however, discrete generative deep learning models have been successfully used to efficiently search high-dimensional discrete spaces. These methods work by representing discrete objects as seq...
متن کاملLifelong learning and second-order learning objects
Current cultural, social, and economic trends challenge traditional concepts of learning and lifelong learning. This paper draws on the twofold nature of learning in a knowledge society and explores options for technological support. The concept of Second-Order Learning Objects is introduced as a potential means to foster generative learning. Generative learning goes beyond that what is already...
متن کاملDevelopment of Generative Learning Objects Using Feature Diagrams and Generative Techniques
Learning Objects (LOs) play a key role for supporting eLearning. In general, however, the development of LOs remains a vague issue, because there is still no clearly defined and widely adopted LO specification and development methodology. We combined two technological paradigms (feature diagrams (FDs) and generative techniques) into a coherent methodology to enhance reusability and productivity...
متن کاملLearning a Generative Model for Validity in Complex Discrete Structures
Deep generative models have been successfully used to learn representations for high-dimensional discrete spaces by representing discrete objects as sequences, for which powerful sequence-based deep models can be employed. Unfortunately, these techniques are significantly hindered by the fact that these generative models often produce invalid sequences: sequences which do not represent any unde...
متن کامل