- initroduced types: BB-RBM GB-RBM, GG-RBM as property of entity

- training simplification and for clarity: added specialized cd_funcs for each entity type

src/rbm/train.py

@@ -1,5 +1,5 @@
 from collections.abc import Callable
-from .matrix import gaussian, sample, prob, rms_error_accu, Mat, np
+from .matrix import sample, sample_gaussian, prob, rms_error_accu, Mat, np
 from .entity import Entity
 from .status import Status
 
@@ -50,7 +50,7 @@ def cd_jens(entity: Entity, v_states: Mat, params: TrainingParams):
 	h_probs = h_states
 
 	if entity.params.do_gaussian_hidden:
-		h_states += gaussian(h_states.shape)
+		h_states += sample_gaussian(h_states)
 	else:
 		h_probs = entity.forward(v_states)
 		if params.do_rao_blackwell:
@@ -83,6 +83,81 @@ def cd_jens(entity: Entity, v_states: Mat, params: TrainingParams):
 
 	return dw, dbv, dbh
 
+def cd_binary_binary(entity: Entity, data_pos: Mat, params: TrainingParams):
+	# Positive phase
+	h_probs_pos = entity.h_given_v(data_pos)
+
+	# Update weights (positive phase)
+	dw = np.dot(np.transpose(data_pos), h_probs_pos)
+	dbh = np.sum(h_probs_pos, 0)
+	dbv = np.sum(data_pos, 0)
+
+	# Sample hidden states
+	if params.do_rao_blackwell:
+		h_states_pos = h_probs_pos
+	else:
+		h_states_pos = sample(h_probs_pos)
+
+	# Negative phase
+	data_neg = entity.v_given_h(h_states_pos)
+	h_probs_neg = entity.h_given_v(data_neg)
+
+	# Gibbs	sampling with training params
+	# ToDo
+
+	# Update weights (negative phase)
+	dw -= np.dot(np.transpose(data_neg), h_probs_neg)
+	dbh -= np.sum(h_probs_neg, 0)
+	dbv -= np.sum(data_neg, 0)
+
+	return dw, dbv, dbh
+
+def cd_gaussian_binary(entity: Entity, data_pos: Mat, params: TrainingParams):
+	# Positive phase
+	h_probs_pos = entity.h_given_v(data_pos)
+
+	# Update weights (positive phase)
+	dw = np.dot(np.transpose(data_pos), h_probs_pos)
+	dbh = np.sum(h_probs_pos, 0)
+	dbv = np.sum(data_pos, 0)
+
+	# Sample hidden states
+	h_states_pos = sample(h_probs_pos)
+
+	# Negative phase
+	data_neg = entity.v_given_h(h_states_pos)
+	h_probs_neg = entity.h_given_v(data_neg)
+
+	# Update weights (negative phase)
+	dw -= np.dot(np.transpose(data_neg), h_probs_neg)
+	dbh -= np.sum(h_probs_neg, 0)
+	dbv -= np.sum(data_neg, 0)
+
+	return dw, dbv, dbh
+
+def cd_gaussian_gaussian(entity: Entity, data_pos: Mat, params: TrainingParams):
+	# Positive phase
+	h_probs_pos = entity.h_given_v(data_pos)
+
+	# Sample hidden states
+	h_states_pos = h_probs_pos + sample_gaussian(h_probs_pos)
+
+	# Update weights (positive phase)
+	dw = np.dot(np.transpose(data_pos), h_states_pos)
+	dbh = np.sum(h_states_pos, 0)
+	dbv = np.sum(data_pos, 0)
+
+	# Negative phase
+	data_neg = entity.v_given_h(h_states_pos)
+	h_probs_neg = entity.h_given_v(data_neg)
+
+	# Update weights (negative phase)
+	dw -= np.dot(np.transpose(data_neg), h_probs_neg)
+	dbh -= np.sum(h_probs_neg, 0)
+	dbv -= np.sum(data_neg, 0)
+
+	return dw, dbv, dbh
+
 def to_mini_batch(batch: Mat, mini_batch_size: int):
 	mini_batches = []
 	remain = batch.shape[0]
@@ -95,12 +170,20 @@ def to_mini_batch(batch: Mat, mini_batch_size: int):
 
 	return mini_batches
 
-def train(entity: Entity, batch: Mat, params: TrainingParams, status: Status, cd_func: Callable = cd_jens):
+def train(entity: Entity, batch: Mat, params: TrainingParams, status: Status):
 	mini_batch_size = min(params.mini_batch_size, batch.shape[0]) if params.mini_batch_size > 0 else batch.shape[0]
 	d_progress = 100.0 / (batch.shape[0]*params.num_epochs)
 	progress = 0
 	keep_running = True
 	status.on_change()
+	cd_func = None
+	if entity.type == Entity.Type.GB_RBM:
+		cd_func = cd_gaussian_binary
+	if entity.type == Entity.Type.BB_RBM:
+		cd_func = cd_binary_binary
+	if entity.type == Entity.Type.GG_RBM:
+		cd_func = cd_gaussian_gaussian
+
 	for mini_batch in to_mini_batch(batch, mini_batch_size):
 		if not keep_running:
 			break