From 3acb6f5ec0e3c0d2c6ceef6eacfea731ef18beb1 Mon Sep 17 00:00:00 2001 From: Alex Auvolat Date: Tue, 28 Jul 2015 15:49:45 -0400 Subject: Memory net mlp 4 --- config/memory_network_mlp_4_momentum.py | 57 +++++++++++++++++++++++++++++++++ 1 file changed, 57 insertions(+) create mode 100644 config/memory_network_mlp_4_momentum.py (limited to 'config/memory_network_mlp_4_momentum.py') diff --git a/config/memory_network_mlp_4_momentum.py b/config/memory_network_mlp_4_momentum.py new file mode 100644 index 0000000..3590732 --- /dev/null +++ b/config/memory_network_mlp_4_momentum.py @@ -0,0 +1,57 @@ +from blocks.initialization import IsotropicGaussian, Constant +from blocks.algorithms import Momentum + +from blocks.bricks import Tanh + +import data +from model.memory_network_mlp import Model, Stream + +n_begin_end_pts = 5 + +dim_embeddings = [ + ('origin_call', data.origin_call_train_size, 10), + ('origin_stand', data.stands_size, 10), + ('week_of_year', 52, 10), + ('day_of_week', 7, 10), + ('qhour_of_day', 24 * 4, 10), + ('day_type', 3, 10), +] + +embed_weights_init = IsotropicGaussian(0.001) + +class MLPConfig(object): + __slots__ = ('dim_input', 'dim_hidden', 'dim_output', 'weights_init', 'biases_init', 'embed_weights_init', 'dim_embeddings') + +prefix_encoder = MLPConfig() +prefix_encoder.dim_input = n_begin_end_pts * 2 * 2 + sum(x for (_, _, x) in dim_embeddings) +prefix_encoder.dim_hidden = [500] +prefix_encoder.weights_init = IsotropicGaussian(0.01) +prefix_encoder.biases_init = Constant(0.001) +prefix_encoder.embed_weights_init = embed_weights_init +prefix_encoder.dim_embeddings = dim_embeddings + +candidate_encoder = MLPConfig() +candidate_encoder.dim_input = n_begin_end_pts * 2 * 2 + sum(x for (_, _, x) in dim_embeddings) +candidate_encoder.dim_hidden = [500] +candidate_encoder.weights_init = IsotropicGaussian(0.01) +candidate_encoder.biases_init = Constant(0.001) +candidate_encoder.embed_weights_init = embed_weights_init +candidate_encoder.dim_embeddings = dim_embeddings + +representation_size = 500 +representation_activation = Tanh + +normalize_representation = False + +step_rule = Momentum(learning_rate=0.1, momentum=0.9) + +batch_size = 10000 +# batch_sort_size = 20 + +# monitor_freq = 2 + +max_splits = 200 + +train_candidate_size = 20000 +valid_candidate_size = 20000 +test_candidate_size = 20000 -- cgit v1.2.3