Пример #1
0
// 根据正则化方法计算偏导数向量需要添加正则化项
func ComputeRegularization(weights *util.Matrix, options OptimizerOptions) *util.Matrix {
	reg := weights.Populate()

	if options.RegularizationScheme == 1 {
		// L-1正则化
		for iLabel := 0; iLabel < weights.NumLabels(); iLabel++ {
			for _, k := range weights.GetValues(iLabel).Keys() {
				if weights.Get(iLabel, k) > 0 {
					reg.Set(iLabel, k, options.RegularizationFactor)
				} else {
					reg.Set(iLabel, k, -options.RegularizationFactor)
				}
			}
		}
	} else if options.RegularizationScheme == 2 {
		// L-2正则化
		for iLabel := 0; iLabel < weights.NumLabels(); iLabel++ {
			for _, k := range weights.GetValues(iLabel).Keys() {
				reg.Set(iLabel, k, options.RegularizationFactor*float64(2)*weights.Get(iLabel, k))
			}
		}
	}

	return reg
}
Пример #2
0
// 计算 z = 1 + sum(exp(sum(w_i * x_i)))
//
// 在temp中保存 exp(sum(w_i * x_i))
func ComputeZ(weights *util.Matrix, features *util.Vector, label int, temp *util.Matrix) float64 {
	result := float64(1.0)
	numLabels := weights.NumLabels() + 1

	for iLabel := 1; iLabel < numLabels; iLabel++ {
		exp := math.Exp(util.VecDotProduct(features, weights.GetValues(iLabel-1)))
		result += exp

		tempVec := temp.GetValues(iLabel - 1)
		if tempVec.IsSparse() {
			for _, k := range features.Keys() {
				tempVec.Set(k, exp)
			}
		} else {
			tempVec.SetAll(exp)
		}
	}
	return result
}
Пример #3
0
func MaxEntComputeInstanceDerivative(
	weights *util.Matrix, instance *data.Instance, instanceDerivative *util.Matrix) {
	// 定义偏导和特征向量
	features := instance.Features

	// 得到维度信息
	numLabels := weights.NumLabels() + 1

	// 计算 z = 1 + exp(sum(w_i * x_i))
	label := instance.Output.Label
	z := ComputeZ(weights, features, label, instanceDerivative)
	inverseZ := float64(1) / z

	for iLabel := 1; iLabel < numLabels; iLabel++ {
		vec := instanceDerivative.GetValues(iLabel - 1)
		if label == 0 || label != iLabel {
			vec.Multiply(inverseZ, 0, features)
		} else {
			vec.Multiply(inverseZ, -1, features)
		}
	}
}