Đề bài
Backpropagation applies the chain rule layer by layer, from the output back to the inputs. The network has n inputs, h hidden neurons and one output, all with sigmoid activation (σ(z) = 1 / (1 + e^(-z))):
- hidden: a_j = σ(inputs · hidden_weights[j] + hidden_biases[j])
- output: y = σ(a · output_weights + output_bias)
- loss: L = (y - target)²
Gradients:
- delta_out = 2 × (y - target) × y × (1 - y)
- Output layer: dL/doutput_weights[j] = delta_out × a_j and dL/doutput_bias = delta_out
- delta_j = delta_out × output_weights[j] × a_j × (1 - a_j)
- Hidden layer: dL/dhidden_weights[j][i] = delta_j × inputs[i] and dL/dhidden_biases[j] = delta_j
Implement backprop_gradients(inputs, hidden_weights, hidden_biases, output_weights, output_bias, target).
Output
Return a matrix with h + 1 rows:
- Row j (for each hidden neuron j, in order): the n gradients of
hidden_weights[j], then the gradient ofhidden_biases[j]. - Last row: the h gradients of
output_weights, then the gradient ofoutput_bias.
Ràng buộc
1 ≤ n, h ≤ 20
-5 ≤ each input, weight and bias ≤ 5
0 ≤ target ≤ 1
Ví dụ
Đầu vào:
inputs = [1.0]
target = 1.0
output_bias = 0.0
hidden_biases = [0.0]
hidden_weights = [
[0.0]
]
output_weights = [0.0]
Kết quả mong đợi:
expected = [
[0.0, 0.0],
[-0.125, -0.25]
]Đầu vào:
std::vector<double> inputs = {1.0};
double target = 1.0;
double output_bias = 0.0;
std::vector<double> hidden_biases = {0.0};
std::vector<std::vector<double>> hidden_weights = {
{0.0}
};
std::vector<double> output_weights = {0.0};
Kết quả mong đợi:
std::vector<std::vector<double>> expected = {
{0.0, 0.0},
{-0.125, -0.25}
};Đầu vào:
double[] inputs = new double[] {1.0};
double target = 1.0;
double output_bias = 0.0;
double[] hidden_biases = new double[] {0.0};
double[][] hidden_weights = new double[][] {
new double[] {0.0}
};
double[] output_weights = new double[] {0.0};
Kết quả mong đợi:
double[][] expected = new double[][] {
new double[] {0.0, 0.0},
new double[] {-0.125, -0.25}
};Giải thích
a = σ(0) = 0.5 and y = σ(0) = 0.5. delta_out = 2 × (0.5 - 1) × 0.25 = -0.25. Output row: [-0.25 × 0.5, -0.25] = [-0.125, -0.25]. delta_1 = -0.25 × 0 × 0.25 = 0, so the hidden row is [0, 0]: a zero output weight blocks the gradient.
Đầu vào:
inputs = [1.0, 0.0]
target = 0.0
output_bias = -1.0
hidden_biases = [0.0, 0.0]
hidden_weights = [
[0.0, 1.0],
[0.0, -1.0]
]
output_weights = [1.0, 1.0]
Kết quả mong đợi:
expected = [
[0.0625, 0.0, 0.0625],
[0.0625, 0.0, 0.0625],
[0.125, 0.125, 0.25]
]Đầu vào:
std::vector<double> inputs = {1.0, 0.0};
double target = 0.0;
double output_bias = -1.0;
std::vector<double> hidden_biases = {0.0, 0.0};
std::vector<std::vector<double>> hidden_weights = {
{0.0, 1.0},
{0.0, -1.0}
};
std::vector<double> output_weights = {1.0, 1.0};
Kết quả mong đợi:
std::vector<std::vector<double>> expected = {
{0.0625, 0.0, 0.0625},
{0.0625, 0.0, 0.0625},
{0.125, 0.125, 0.25}
};Đầu vào:
double[] inputs = new double[] {1.0, 0.0};
double target = 0.0;
double output_bias = -1.0;
double[] hidden_biases = new double[] {0.0, 0.0};
double[][] hidden_weights = new double[][] {
new double[] {0.0, 1.0},
new double[] {0.0, -1.0}
};
double[] output_weights = new double[] {1.0, 1.0};
Kết quả mong đợi:
double[][] expected = new double[][] {
new double[] {0.0625, 0.0, 0.0625},
new double[] {0.0625, 0.0, 0.0625},
new double[] {0.125, 0.125, 0.25}
};Giải thích
Both hidden values are σ(0) = 0.5, so y = σ(0.5 + 0.5 - 1) = 0.5 and delta_out = 2 × 0.5 × 0.25 = 0.25. Output row: [0.125, 0.125, 0.25]. Each delta_j = 0.25 × 1 × 0.25 = 0.0625, giving hidden rows [0.0625, 0, 0.0625] (the second input is 0).
Hướng tiếp cận
Hãy tự thử trước, sau đó mở từng gợi ý một.
Gợi ý 1
Work backward from the output neuron first, then reuse that signal to compute each hidden neuron's contribution.
Gợi ý 2
You need one delta for the output layer and one delta per hidden neuron, both based on sigmoid derivatives.
Gợi ý 3
Be careful to use each hidden neuron's own output weight when propagating error back to that neuron.
Độ phức tạp mong đợi
O(hn) time, O(hn) extra space
Tham khảo
Thử thách này đã được điều chỉnh cho CodeUtility. Hãy làm theo đề bài và các ràng buộc ở trên.