What is TanhLayer in PyBrain

In this article, we will be looking at various functionality with the defined examples of the TanhLayer in PyBrain. Layers in Pybrain are functions that are used on hidden layers of the network. TanhLayer executes the tanh squashing function.

Syntax:

Import TanhLayer: from pybrain.structure import TanhLayer

Use in python code: net = buildNetwork(2, 3, 1, bias=True, hiddenclass=TanhLayer)

Example 1:

In this example, we import the TanhLayer using the import command to create the network using buildNetwork() with input, hidden, and output layer. We take a hidden class as TanhLayer, Now give the sizes of input and output dataset using SupervisedDataSet(). To add sample dataset to AND table and NOR table. Then train this network using BackpropTrainer(). We have 2500 iterations and then testing starts and we can see the errors, corrections, max, errors, etc.In this case, the sample data we have taken in AND table are ((0,0), (0,)) and ((0,1),(1,)) and NOR table are ((0,0),(0,)) and (0,1),(1,))

Python

from pybrain.tools.shortcuts import buildNetwork
from pybrain.structure import TanhLayer
from pybrain.datasets import SupervisedDataSet
from pybrain.supervised.trainers import BackpropTrainer

# two inputs, two hidden, and one output
net = buildNetwork(2, 3, 1, bias=True, hiddenclass=TanhLayer)
gate_set = SupervisedDataSet(2, 1)
test_dataset = SupervisedDataSet(2, 1)

# AND truth table
gate_set.addSample((0, 0), (0,))
gate_set.addSample((0, 1), (1,))


# NOR truth table
test_dataset.addSample((0, 0), (0,))
test_dataset.addSample((0, 1), (1,))

# Train the network with net and gate_set
backpr_tr = BackpropTrainer(net, gate_set)

# 2500 iteration
for i in range(2500):
      backpr_tr.train()

# Testing....
backpr_tr.testOnData(dataset=test_dataset, verbose = True)

Output:

Example 2:

Under this example, the sample data we have taken in AND table are ((0,0), (1,)) and ((0,1),(1,)) and NOR table are ((0,0),(0,)) and (0,1),(0,)) and we can see the testing output with average errors, max errors, median errors, etc.

Python

from pybrain.tools.shortcuts import buildNetwork
from pybrain.structure import TanhLayer
from pybrain.datasets import SupervisedDataSet
from pybrain.supervised.trainers import BackpropTrainer

# two inputs, two hidden, and one output
net = buildNetwork(2, 3, 1, bias=True, hiddenclass=TanhLayer)
gate_set = SupervisedDataSet(2, 1)
test_dataset = SupervisedDataSet(2, 1)

# AND truth table
gate_set.addSample((0, 0), (1,))
gate_set.addSample((0, 1), (1,))

# NOR truth table
test_dataset.addSample((0, 0), (0,))
test_dataset.addSample((0, 1), (0,))

#Train the network with net and gate_set
backpr_tr = BackpropTrainer(net, gate_set)

# 2500 iteration
for i in range(2500):
      backpr_tr.train()

# Testing....
backpr_tr.testOnData(dataset=test_dataset, verbose = True)

Output: