chainer.functions.black_out¶

chainer.functions.black_out(x, t, W, samples, reduce='mean')[source]¶

BlackOut loss function.

BlackOut loss function is defined as

$-\log(p(t)) - \sum_{s \in S} \log(1 - p(s)),$

where $t$ is the correct label, $S$ is a set of negative examples and $p(\cdot)$ is likelihood of a given label. And, $p$ is defined as

$p(y) = \frac{\exp(W_y^\top x)}{ \sum_{s \in samples} \exp(W_s^\top x)}.$

The output is a variable whose value depends on the value of the option reduce. If it is 'no', it holds the no loss values. If it is 'mean', this function takes a mean of loss values.

Parameters

x (Variable or N-dimensional array) – Batch of input vectors. Its shape should be $(N, D)$ .
t (Variable or N-dimensional array) – Vector of ground truth labels. Its shape should be $(N,)$ . Each elements $v$ should satisfy $0 \geq v \geq V$ or $-1$ where $V$ is the number of label types.
W (Variable or N-dimensional array) – Weight matrix. Its shape should be $(V, D)$
samples (Variable) – Negative samples. Its shape should be $(N, S)$ where $S$ is the number of negative samples.
reduce (str) – Reduction option. Its value must be either 'no' or 'mean'. Otherwise, ValueError is raised.

Returns

A variable object holding loss value(s). If reduce is 'no', the output variable holds an array whose shape is $(N,)$ . If it is 'mean', it holds a scalar.

Return type

Variable

See: BlackOut: Speeding up Recurrent Neural Network Language Models With Very Large Vocabularies