Abstract—We propose a system with multiple mobile agents, which will have a shared intelligence. Such architecture will enable the entire system to become ‘smarter’ as each individual agent has new experiences and learns about new things. Whenever each node learns something new, it makes its peers learn, thus greatly accelerating the rate of learning of the entire system. The color, shape and size of an image are extracted. An attempt is made to identify the object in the image using its local intelligence. Next, it tries to learn about the object from its peers. If none of its peers know about the object, it simply learns about the object from the user, and updates its own knowledgebase. When a similar object is encountered at a later stage, the system is able to recognize the object based on its own knowledge, or from its peers’ knowledge – similar to how humans learn.
Index Terms—Artificial intelligence, recognition, learning, distributed systems, Android, image processing.
The authors are with Department of Computer Science and Engineering, Vidyalankar Institute of Technology, University of Mumbai, India (e-mail: omkarpimple1991@gmail.com, ume7715@gmail.com, nehagavankar1992@gmail.com).
Cite: Omkar Pimple, Umesh Saravane, and Neha Gavankar, "Cognitive Learning Using Distributed Artificial Intelligence," International Journal of Machine Learning and Computing vol. 5, no. 1, pp. 7-11, 2015.