Alternative names (2)
ruleChange • ruleModificationRandom triples
| Subject | Object |
|---|---|
| gptkb:2015_NLDS_slide | led to new slide rule (Utley Rule) |
| gptkb:Dead-ball_era | ban on spitball in 1920 |
| gptkb:Momentum_optimizer | velocity-based |
| gptkb:Adam_optimizer | uses bias-corrected first and second moment estimates |
| gptkb:Moran_process | one individual reproduces, one individual dies per time step |
| gptkb:least_mean_squares_(LMS)_algorithm | w(n+1) = w(n) + μ e(n) x(n) |
| gptkb:Trust_Region_Policy_Optimization | constrained optimization |
| gptkb:ADALINE_rule | weights updated based on error |
| gptkb:Adam_Optimizer | uses first and second moment estimates |
| gptkb:WCST | rules change without warning |
| gptkb:Ross_Chastain's_wall_ride_maneuver | NASCAR banned similar moves for future races |
| gptkb:Q-Learning | gptkb:Bellman_equation |
| gptkb:binary_PSO | sigmoid function |
| gptkb:Adam_optimizer | parameter update based on moving averages of gradient and squared gradient |
| gptkb:Stochastic_gradient_descent | parameter update using single or few samples |
| gptkb:Least_Mean_Squares_(LMS)_algorithm | w(n+1) = w(n) + μ e(n) x(n) |
| gptkb:Kohonen_map | neighborhood adaptation |
| gptkb:NaSch_model | randomization |
| gptkb:REINFORCE_algorithm | gradient ascent |
| gptkb:Q-learning_algorithm | Q(s,a) ← Q(s,a) + α [r + γ max Q(s',a') - Q(s,a)] |