Alternative names (2)
ruleChange • ruleModificationRandom triples
| Subject | Object |
|---|---|
| gptkb:Elo_rating_system | rating changes after each game |
| gptkb:Least_Mean_Squares_(LMS)_algorithm | w(n+1) = w(n) + μ e(n) x(n) |
| gptkb:Momentum_optimizer | velocity-based |
| gptkb:Adam_optimizer | parameter update based on moving averages of gradient and squared gradient |
| gptkb:Global_Rapid_Rugby | faster restarts |
| gptkb:Hopfield_network | asynchronous |
| gptkb:NaSch_model | randomization |
| gptkb:recursive_least_squares_(RLS)_algorithm | Kalman filter-like recursion |
| gptkb:Conway's_Game_of_Life | synchronous |
| gptkb:Para_7-a-side_National_Team | no offside rule |
| gptkb:binary_PSO | sigmoid function |
| gptkb:State-Action-Reward-State-Action | Q(s,a) ← Q(s,a) + α [r + γ Q(s',a') - Q(s,a)] |
| gptkb:L-BFGS_algorithm | approximates inverse Hessian matrix |
| gptkb:TD(0) | V(s) ← V(s) + α [r + γ V(s') − V(s)] |
| gptkb:RMSProp | divides learning rate by moving average of squared gradients |
| gptkb:Least_Mean_Squares | w(n+1) = w(n) + μ e(n) x(n) |
| gptkb:ADALINE_rule | weights updated based on error |
| gptkb:Least_Mean_Squares_(LMS) | w(n+1) = w(n) + μ e(n) x(n) |
| gptkb:Adam_optimizer | uses bias-corrected first and second moment estimates |
| gptkb:Particle_Swarm_Optimization | position update |