How to build a single layer neural network model using theano?

Recipe Objective - How to build a single-layer neural network model using theano?

Let's try to build a single layer neural network model, where x1 and x2 are input neurons, b is bias and o is output neuron.

For more related projects -

/projects/data-science-projects/keras-deep-learning-projects
/projects/data-science-projects/neural-network-projects

Example -

# Importing libraries
import theano
from theano import tensor
from theano.ifelse import ifelse

# Creating variables
# Input neuron
x = tensor.vector('x')

# Weight
w = tensor.vector('w')

# Bias
b = tensor.scalar('b')

# Creating expression:
z = tensor.dot(x,w)+b

# Output neuron
o = ifelse(tensor.lt(z,0),0,1)

fun_neural_network = theano.function([x,w,b],o)

# Defining Inputs, Weights and bias
inputs = [ [0, 0], [0, 1], [1, 0], [1, 1] ]
weights = [ 1, 1]
bias = 0

# Iterate through all inputs and find outputs:
for ip in range(len(inputs)):
 m = inputs[ip]
 out = fun_neural_network(m,weights,bias)
 print('The output for x1 = {} & x2 = {} is {}'.format(m[0],m[1],out))


Output -
The output for x1 = 0 & x2 = 0 is 1
The output for x1 = 0 & x2 = 1 is 1
The output for x1 = 1 & x2 = 0 is 1
The output for x1 = 1 & x2 = 1 is 1

In this way, we can build a single-layer neural network model using theano.