Alternative names (2)
ruleChange • ruleModificationRandom triples
| Subject | Object |
|---|---|
| gptkb:ADALINE_rule | weights updated based on error |
| gptkb:Least_Mean_Squares_(LMS)_algorithm | w(n+1) = w(n) + μ e(n) x(n) |
| gptkb:L-BFGS_algorithm | approximates inverse Hessian matrix |
| gptkb:Global_Rapid_Rugby | faster restarts |
| gptkb:Exponentially_Weighted_Recursive_Least_Squares | recursive |
| gptkb:Least_Mean_Squares | w(n+1) = w(n) + μ e(n) x(n) |
| gptkb:1983-84_NHL_season_(regular_season_overtime) | reintroduction of regular season overtime |
| gptkb:Hopfield_networks | synchronous |
| gptkb:Kohonen_map | winner-takes-all |
| gptkb:Adam_Optimizer | uses first and second moment estimates |
| gptkb:Policy_Gradient | Gradient Ascent |
| gptkb:Para_7-a-side_National_Team | no offside rule |
| gptkb:Adam_optimizer | parameter update based on moving averages of gradient and squared gradient |
| gptkb:recursive_least_squares_(RLS)_algorithm | Kalman filter-like recursion |
| gptkb:Three-check | normal chess rules apply except for win condition |
| gptkb:Global_Rapid_Rugby | power try |
| gptkb:LMS_algorithm | w(n+1) = w(n) + μ e(n) x(n) |
| gptkb:NaSch_model | deceleration |
| gptkb:Q-learning_algorithm | Q(s,a) ← Q(s,a) + α [r + γ max Q(s',a') - Q(s,a)] |
| gptkb:REINFORCE_algorithm | gradient ascent |