Skip to Main Content
 

Global Search Box

 
 
 

ETD Abstract Container

Abstract Header

Implementation of Memory for Cognitive Agents Using Biologically Plausible Associative Pulsing Neurons

., Basawaraj
http://orcid.org/0000-0003-2584-9652
http://rave.ohiolink.edu/etdc/view?acc_num=ohiou1561721551043877

Abstract Details

2019, Doctor of Philosophy (PhD), Ohio University, Electrical Engineering & Computer Science (Engineering and Technology).
Artificial intelligence (AI) is being widely applied to various practical problems, and researchers are working to address numerous issues facing the field. The organizational structure and learning mechanism of the memory is one such issue. A cognitive agent builds a representation of its environment and remembers its experiences to interpret its inputs and implements its goals through its actions. By doing so it demonstrates its intelligence (if any), and it is its learning mechanism, value system and sensory motor coordination that makes all this possible. Memory in a cognitive agent stores its knowledge, knowledge gained over a life-time of experiences in a specific environment. That is, memory includes the “facts”, the relationships between them, and the mechanism used to learn, recognize, and recall based on the agent’s interaction with the world/environment. It remembers events that the agent experienced reflecting important actions and observations. It motivates the agent to do anything by providing assessment of the state of the environment and its own state. It allows it to plan and anticipate. And finally, it allows the agent to reflect on itself as an independent being. Hence, memory is critical for intelligence, for it is the memory that determines a cognitive agent’s abilities and learning skills. Research has shown that while memory in humans can be classified into different types, based on factors such as their longevity and cognitive mechanisms used to create and retrieve them, they all are achieved using a similar underlying structure. The focus of this dissertation was on using this principle, i.e. different memories created using the same underlying structure, to implement memory for cognitive agents using a biologically plausible model of neuron. This work was an attempt to demonstrate the feasibility of implementing self-organizing memory structures capable of performing the various memory related tasks necessary for a cognitive agent using a computationally feasible model of biologically inspired neuron. For the purpose of this work the memory capabilities were limited to those necessary for a cognitive agent capable of solving some simple problem, say satisfying its hunger, and in the process creating some high-level abstract needs such as increasing food supply and learning to address them, eventually creating a set of abstract pains and goals. Intelligence requires the ability to learn, and a cognitive agent can demonstrate its intelligence through learning from its experiences and observations to solve problems. In this work it was assumed that the following capabilities: ability to recognize objects, ability to recognize sequences, form relationships between information in the memory, make predictions/anticipate, and demonstrate creativity were necessary for a cognitive agent to learn to solve a problem and demonstrate its intelligence. Subsequent to providing proof that these abilities were necessary for a cognitive agent capable of learning to solve a problem that required creation of a set of abstract pains and goals, a biologically plausible associative pulsing neuron model was introduced. This neuron model was subsequently used to implement various memory structures and learning mechanisms to demonstrate the above mentioned memory capabilities. The declarative memory implemented demonstrated the ability to create semantic relationships and demonstrated creativity. The ability to recognize sequences was demonstrated by both the episodic memory and the structure resulting from the lumped minicolumn associative knowledge graph (LUMAKG) algorithm. LUMAKG structure also demonstrated the ability to create semantic relationships and make predictions. Finally an associative pulsing neural network (APNN) structure created using an associative adaption process demonstrated its ability to recognize objects. The implemented memory structures were tested on various datasets, e.g. MNIST, children’s book test, and yeast, and their performances compared to various state of the art techniques. The results demonstrated that the memory structures implemented in this work had performance better than or comparable to other techniques. Finally, the results of this dissertation demonstrate the feasibility of building memory for a cognitive agent based upon a single computational unit, i.e. neuron model, and simple learning mechanisms.
Wojciech Jadwisienczak (Advisor)
161 p.
Electrical Engineering
Associative memory; minicolumn structure; knowledge representation; object recognition; embodied intelligence

Recommended Citations

Citations

  • ., B. (2019). Implementation of Memory for Cognitive Agents Using Biologically Plausible Associative Pulsing Neurons [Doctoral dissertation, Ohio University]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=ohiou1561721551043877

    APA Style (7th edition)

  • ., Basawaraj. Implementation of Memory for Cognitive Agents Using Biologically Plausible Associative Pulsing Neurons. 2019. Ohio University, Doctoral dissertation. OhioLINK Electronic Theses and Dissertations Center, http://rave.ohiolink.edu/etdc/view?acc_num=ohiou1561721551043877.

    MLA Style (8th edition)

  • ., Basawaraj. "Implementation of Memory for Cognitive Agents Using Biologically Plausible Associative Pulsing Neurons." Doctoral dissertation, Ohio University, 2019. http://rave.ohiolink.edu/etdc/view?acc_num=ohiou1561721551043877

    Chicago Manual of Style (17th edition)

ohiou1561721551043877
51
© 2019, all rights reserved.
This open access ETD is published by Ohio University and OhioLINK.