Related Experiment Videos
BAM learning of nonlinearly separable tasks by using an asymmetrical output function and reinforcement learning
Sylvain Chartier1, Mounir Boukadoum, Mahmood Amiri
1School of Psychology, University of Ottawa, Ottawa, ON K1N 6N5 Canada. sylvain.chartier@uottawa.ca
IEEE Transactions on Neural Networks
|July 15, 2009
Summary
New bidirectional associative memory (BAM) models use an asymmetry parameter to improve recall. This chaotic BAM approach enhances learning and recall performance, modeling supervised, reinforcement, and unsupervised learning for cognitive and engineering applications.
Area of Science:
- Artificial Intelligence
- Computational Neuroscience
- Machine Learning
Background:
- Traditional bidirectional associative memory (BAM) networks rely on symmetrical output functions for stable memory recall.
- Existing BAM models often struggle with complex, nonlinearly separable patterns and lack flexibility in learning paradigms.
Purpose of the Study:
- To introduce an asymmetry parameter into a chaotic BAM output function to enhance memory recall and control associative learning.
- To demonstrate the capability of the modified BAM framework to model supervised, reinforcement, and unsupervised learning.
- To evaluate the performance improvement of a hybrid BAM-GRNN model for learning and recall.
Main Methods:
- Incorporation of an asymmetry parameter into a chaotic BAM output function to bias the search space and control attractor dynamics.
- Implementation of reinforcement learning to enable the storage and recall of nonlinearly separable patterns.
- Development and simulation of a hybrid model combining the enhanced BAM with a general regression neural network (GRNN).
Main Results:
- The asymmetry parameter allows prior knowledge to temporarily disable attractors, improving recall performance by controlling chaotic wandering.
- The modified BAM framework successfully models three distinct learning types: supervised, reinforcement, and unsupervised.
- Simulations show a significant increase in BAM learning and recall performance when integrated with GRNN.
Conclusions:
- The proposed asymmetric chaotic BAM offers a unified framework for diverse learning types, proving valuable for cognitive modeling.
- The hybrid BAM-GRNN model demonstrates enhanced engineering utility with notable improvements in learning and recall efficiency.
- This research advances BAM networks by providing greater control over memory dynamics and expanding their applicability to complex pattern recognition tasks.
Related Concept Videos
01:27Associative Learning
Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...
Classical conditioning, also known...
01:12Observational Learning
Albert Bandura's observational learning, also known as imitation or modeling, occurs when a person observes and imitates another's behavior. It is a quicker process than operant conditioning. A well-known example is the Bobo doll study, where children who saw an adult acting aggressively towards the doll were more likely to act aggressively when left alone, compared to those who observed a nonaggressive adult. Many psychologists view observational learning as a form of latent learning because...
01:14Avoidance Learning and Learned Helplessness
Avoidance learning and learned helplessness are critical concepts in understanding behavioral responses to negative stimuli.
Avoidance learning occurs when an organism learns that a specific behavior can prevent an unpleasant outcome. For example, a student who receives a bad grade may start studying harder to avoid future poor grades. This behavior persists even when the negative outcome is no longer present. Avoidance learning is powerful because it maintains behavior in the absence of the...
Avoidance learning occurs when an organism learns that a specific behavior can prevent an unpleasant outcome. For example, a student who receives a bad grade may start studying harder to avoid future poor grades. This behavior persists even when the negative outcome is no longer present. Avoidance learning is powerful because it maintains behavior in the absence of the...