Associative Fine-Tuning of Biologically Inspired Active Neuro-Associative Knowledge Graphs
- Resource Type
- Conference
- Authors
- Horzyk, Adrian; Starzyk, Janusz A.
- Source
- 2018 IEEE Symposium Series on Computational Intelligence (SSCI) Computational Intelligence (SSCI), 2018 IEEE Symposium Series on. :2068-2075 Nov, 2018
- Subject
- Aerospace
Bioengineering
Computing and Processing
Power, Energy and Industry Applications
Robotics and Control Systems
Signal Processing and Analysis
Transportation
Computational intelligence
Knowledge engineering
Biomedical engineering
Information technology
Biological neural networks
Deep learning
Tuning
brain-inspired associative learning
spiking neural networks
deep learning
tuning of weights
sequential patterns
associative representation of knowledge
active neuro-associative knowledge graphs
hetero-associative memory
- Language
This paper introduces a new tuning algorithm that improves the associative training algorithm of active neuro-associative knowledge graphs (ANAKG). We also expand the definition of synaptic weights, using new multiplicative factors. Biological neural networks are sparse and developed in neuronal plasticity processes adapting them to the repeatable combinations of the input stimuli. Real neurons connect conditionally according to neural activity and on demand of some biochemical processes. They do not connect to all neurons in subsequent layers as is usually performed in artificial neural networks. For more than a decade, scientists conducted extensive research on adaptation mechanisms which use sparsely connected neural structures that can specialize and adapt faster to training data. This approach is also widely used in various learning strategies of deep neural networks. Conditional creation of sparse connections and fin e-tuning of their weights in complex associative neuronal ANAKG structures are the main contributions of this paper. The significant improvement of recalling of the context-based associations was verified experimentally.