Perceptron (Hebb) learning rule (Geron Ch 10, morie.fn grhbb)

Usage

morie_geron_hebb_rule_grhbb(x, y_true, y_pred, w, eta)

Arguments

x: Input vector.
y_true, y_pred: Target and predicted outputs.
w: (n_in, n_out) weights.
eta: Positive learning rate.

Value

List with w_new, delta_w, error, converged, update_norm.

Examples

morie_geron_hebb_rule_grhbb(c(1, 2), c(1, 0), c(0, 1), matrix(c(0.5,
    0.5, 1, -1), 2, byrow = TRUE), 0.1)
#> $w_new
#>      [,1] [,2]
#> [1,]  0.6  0.4
#> [2,]  1.2 -1.2
#> 
#> $delta_w
#>      [,1] [,2]
#> [1,]  0.1 -0.1
#> [2,]  0.2 -0.2
#> 
#> $error
#> [1]  1 -1
#> 
#> $converged
#> [1] FALSE
#> 
#> $update_norm
#> [1] 0.3162278
#> 
#> $eta
#> [1] 0.1
#> 
#> $estimate
#>      [,1] [,2]
#> [1,]  0.6  0.4
#> [2,]  1.2 -1.2
#> 
#> $n
#> [1] 2
#>