nplm.py 文件源码

def train(self, sentences, iterations=1000):
        # Preprocess sentences to create indices of context and next words
        self.dictionary = build_dictionary(sentences, self.vocabulary_size)
        indices = to_indices(sentences, self.dictionary)
        self.reverse_dictionary = {index: word for word, index in self.dictionary.items()}
        inputs, outputs = self.create_context(indices)

        # Create cost and gradient function for gradient descent
        shapes = [self.W_shape, self.U_shape, self.H_shape, self.C_shape]
        flatten_nplm_cost_gradient = flatten_cost_gradient(nplm_cost_gradient, shapes)
        cost_gradient = bind_cost_gradient(flatten_nplm_cost_gradient, inputs, outputs,
                                           sampler=get_stochastic_sampler(10))

        # Train neural network
        parameters_size = np.sum(np.product(shape) for shape in shapes)
        initial_parameters = np.random.normal(size=parameters_size)
        self.parameters, cost_history = gradient_descent(cost_gradient, initial_parameters, iterations)
        return cost_history