Reinforced snap-drift learning for proxylet selection in active computer networks

Keyphrases

• Snapping 100%
• Computer Networks 100%
• Reinforced 100%
• Learning Styles 75%
• Input Pattern 50%
• Adaptive Resonance Theory 50%
• User Request 25%
• Neural Network System 25%
• Hybrid Form 25%
• Performance Requirements 25%
• Continual Learning 25%
• New Pattern 25%
• Learning Vector Quantization 25%
• Simulation Environment 25%
• Slow Drift 25%
• Successful Adaptation 25%
• Two-mode 25%
• Modular Neural Network 25%
• Learning Methods 25%
• Performance Improvement 25%
• New Performance 25%
• Self-organization 25%
• Performance Level 25%
• Minimalist 25%
• Non-stationary Environments 25%
• Pattern Learning 25%
• Service Selection 25%
• Computer Network Simulation 25%

Computer Science

• Computer Network 100%
• Learning Style 100%
• Network Simulation 50%
• Vector Quantization 50%
• Simulation Environment 50%
• Neural Network 50%
• Performance Requirement 50%

Chemical Engineering

• Neural Network 100%