Related
I am trying to create a multi-layered perceptron for the purpose of classifying a dataset of hand drawn digits obtained from the MNIST database. It implements 2 hidden layers that have a sigmoid activation function while the output layer utilizes SoftMax. However, for whatever reason I am not able to get it to work. I have attached the training loop from my code below, this I am confident is where the problems stems from. Can anyone identify possible issues with my implementation of the perceptron?
def train(self, inputs, targets, eta, niterations):
"""
inputs is a numpy array of shape (num_train, D) containing the training images
consisting of num_train samples each of dimension D.
targets is a numpy array of shape (num_train, D) containing the training labels
consisting of num_train samples each of dimension D.
eta is the learning rate for optimization
niterations is the number of iterations for updating the weights
"""
ndata = np.shape(inputs)[0] # number of data samples
# adding the bias
inputs = np.concatenate((inputs, -np.ones((ndata, 1))), axis=1)
# numpy array to store the update weights
updatew1 = np.zeros((np.shape(self.weights1)))
updatew2 = np.zeros((np.shape(self.weights2)))
updatew3 = np.zeros((np.shape(self.weights3)))
for n in range(niterations):
# forward phase
self.outputs = self.forwardPass(inputs)
# Error using the sum-of-squares error function
error = 0.5*np.sum((self.outputs-targets)**2)
if (np.mod(n, 100) == 0):
print("Iteration: ", n, " Error: ", error)
# backward phase
deltao = self.outputs - targets
placeholder = np.zeros(np.shape(self.outputs))
for j in range(np.shape(self.outputs)[1]):
y = self.outputs[:, j]
placeholder[:, j] = y * (1 - y)
for y in range(np.shape(self.outputs)[1]):
if not y == j:
placeholder[:, j] += -y * self.outputs[:, y]
deltao *= placeholder
# compute the derivative of the second hidden layer
deltah2 = np.dot(deltao, np.transpose(self.weights3))
deltah2 = self.hidden2*self.beta*(1.0-self.hidden2)*deltah2
# compute the derivative of the first hidden layer
deltah1 = np.dot(deltah2[:, :-1], np.transpose(self.weights2))
deltah1 = self.hidden1*self.beta*(1.0-self.hidden1)*deltah1
# update the weights of the three layers: self.weights1, self.weights2 and self.weights3
updatew1 = eta*(np.dot(np.transpose(inputs),deltah1[:, :-1])) + (self.momentum * updatew1)
updatew2 = eta*(np.dot(np.transpose(self.hidden1),deltah2[:, :-1])) + (self.momentum * updatew2)
updatew3 = eta*(np.dot(np.transpose(self.hidden2),deltao)) + (self.momentum * updatew3)
self.weights1 -= updatew1
self.weights2 -= updatew2
self.weights3 -= updatew3
def forwardPass(self, inputs):
"""
inputs is a numpy array of shape (num_train, D) containing the training images
consisting of num_train samples each of dimension D.
"""
# layer 1
# the forward pass on the first hidden layer with the sigmoid function
self.hidden1 = np.dot(inputs, self.weights1)
self.hidden1 = 1.0/(1.0+np.exp(-self.beta*self.hidden1))
self.hidden1 = np.concatenate((self.hidden1, -np.ones((np.shape(self.hidden1)[0], 1))), axis=1)
# layer 2
# the forward pass on the second hidden layer with the sigmoid function
self.hidden2 = np.dot(self.hidden1, self.weights2)
self.hidden2 = 1.0/(1.0+np.exp(-self.beta*self.hidden2))
self.hidden2 = np.concatenate((self.hidden2, -np.ones((np.shape(self.hidden2)[0], 1))), axis=1)
# output layer
# the forward pass on the output layer with softmax function
outputs = np.dot(self.hidden2, self.weights3)
outputs = np.exp(outputs)
outputs /= np.repeat(np.sum(outputs, axis=1),outputs.shape[1], axis=0).reshape(outputs.shape)
return outputs
Update: I have since figured something out that I messed up during the backpropagation of the SoftMax algorithm. The actual deltao should be:
deltao = self.outputs - targets
placeholder = np.zeros(np.shape(self.outputs))
for j in range(np.shape(self.outputs)[1]):
y = self.outputs[:, j]
placeholder[:, j] = y * (1 - y)
# the counter for the for loop below used to also be named y causing confusion
for i in range(np.shape(self.outputs)[1]):
if not i == j:
placeholder[:, j] += -y * self.outputs[:, i]
deltao *= placeholder
After this correction the overflow errors have seemed to have sorted themselves however, there is now a new problem, no matter my efforts the accuracy of the perceptron does not exceed 15% no matter what variables I change
Second Update: After a long time I have finally found a way to get my code to work. I had to change the backpropogation of SoftMax (in code this is called deltao) to the following:
deltao = np.exp(self.outputs)
deltao/=np.repeat(np.sum(deltao,axis=1),deltao.shape[1]).reshape(deltao.shape)
deltao = deltao * (1 - deltao)
deltao *= (self.outputs - targets)/np.shape(inputs)[0]
Only problem is I have no idea why this works as a derivative of SoftMax could anyone explain this?
Given the XOR problem:
X = xor_input = np.array([[0,0], [0,1], [1,0], [1,1]])
Y = xor_output = np.array([[0,1,1,0]]).T
And a simple
two layered Multi-Layered Perceptron (MLP) with
sigmoid activations between them and
Mean Square Error (MSE) as the loss function/optimization criterion
[code]:
def sigmoid(x): # Returns values that sums to one.
return 1 / (1 + np.exp(-x))
def sigmoid_derivative(sx): # For backpropagation.
# See https://math.stackexchange.com/a/1225116
return sx * (1 - sx)
# Cost functions.
def mse(predicted, truth):
return np.sum(np.square(truth - predicted))
X = xor_input = np.array([[0,0], [0,1], [1,0], [1,1]])
Y = xor_output = np.array([[0,1,1,0]]).T
# Define the shape of the weight vector.
num_data, input_dim = X.shape
# Lets set the dimensions for the intermediate layer.
hidden_dim = 5
# Initialize weights between the input layers and the hidden layer.
W1 = np.random.random((input_dim, hidden_dim))
# Define the shape of the output vector.
output_dim = len(Y.T)
# Initialize weights between the hidden layers and the output layer.
W2 = np.random.random((hidden_dim, output_dim))
And given the stopping criteria as a fixed no. of epochs (no. of iterations through the X and Y) with a fixed learning rate of 0.3:
# Initialize weigh
num_epochs = 10000
learning_rate = 0.3
When I run through the forward-backward propagation and update the weights in each epoch, how should I update the weights?
I tried to simply add the product of the learning rate with the dot product of the backpropagated derivative with the layer outputs but the model still only updated the weights in one direction causing all the weights to degrade to near zero.
for epoch_n in range(num_epochs):
layer0 = X
# Forward propagation.
# Inside the perceptron, Step 2.
layer1 = sigmoid(np.dot(layer0, W1))
layer2 = sigmoid(np.dot(layer1, W2))
# Back propagation (Y -> layer2)
# How much did we miss in the predictions?
layer2_error = mse(layer2, Y)
#print(layer2_error)
# In what direction is the target value?
# Were we really close? If so, don't change too much.
layer2_delta = layer2_error * sigmoid_derivative(layer2)
# Back propagation (layer2 -> layer1)
# How much did each layer1 value contribute to the layer2 error (according to the weights)?
layer1_error = np.dot(layer2_delta, W2.T)
layer1_delta = layer1_error * sigmoid_derivative(layer1)
# update weights
W2 += - learning_rate * np.dot(layer1.T, layer2_delta)
W1 += - learning_rate * np.dot(layer0.T, layer1_delta)
#print(np.dot(layer0.T, layer1_delta))
#print(epoch_n, list((layer2)))
# Log the loss value as we proceed through the epochs.
losses.append(layer2_error.mean())
How should the weights be updated correctly?
Full code:
from itertools import chain
import matplotlib.pyplot as plt
import numpy as np
np.random.seed(0)
def sigmoid(x): # Returns values that sums to one.
return 1 / (1 + np.exp(-x))
def sigmoid_derivative(sx):
# See https://math.stackexchange.com/a/1225116
return sx * (1 - sx)
# Cost functions.
def mse(predicted, truth):
return np.sum(np.square(truth - predicted))
X = xor_input = np.array([[0,0], [0,1], [1,0], [1,1]])
Y = xor_output = np.array([[0,1,1,0]]).T
# Define the shape of the weight vector.
num_data, input_dim = X.shape
# Lets set the dimensions for the intermediate layer.
hidden_dim = 5
# Initialize weights between the input layers and the hidden layer.
W1 = np.random.random((input_dim, hidden_dim))
# Define the shape of the output vector.
output_dim = len(Y.T)
# Initialize weights between the hidden layers and the output layer.
W2 = np.random.random((hidden_dim, output_dim))
# Initialize weigh
num_epochs = 10000
learning_rate = 0.3
losses = []
for epoch_n in range(num_epochs):
layer0 = X
# Forward propagation.
# Inside the perceptron, Step 2.
layer1 = sigmoid(np.dot(layer0, W1))
layer2 = sigmoid(np.dot(layer1, W2))
# Back propagation (Y -> layer2)
# How much did we miss in the predictions?
layer2_error = mse(layer2, Y)
#print(layer2_error)
# In what direction is the target value?
# Were we really close? If so, don't change too much.
layer2_delta = layer2_error * sigmoid_derivative(layer2)
# Back propagation (layer2 -> layer1)
# How much did each layer1 value contribute to the layer2 error (according to the weights)?
layer1_error = np.dot(layer2_delta, W2.T)
layer1_delta = layer1_error * sigmoid_derivative(layer1)
# update weights
W2 += - learning_rate * np.dot(layer1.T, layer2_delta)
W1 += - learning_rate * np.dot(layer0.T, layer1_delta)
#print(np.dot(layer0.T, layer1_delta))
#print(epoch_n, list((layer2)))
# Log the loss value as we proceed through the epochs.
losses.append(layer2_error.mean())
# Visualize the losses
plt.plot(losses)
plt.show()
Am I missing anything in the backpropagation?
Maybe I missed out the derivative from the cost to the second layer?
Edited
I realized I missed the partial derivative from the cost to the second layer and after adding it:
# Cost functions.
def mse(predicted, truth):
return 0.5 * np.sum(np.square(predicted - truth)).mean()
def mse_derivative(predicted, truth):
return predicted - truth
With the updated backpropagation loop across epochs:
for epoch_n in range(num_epochs):
layer0 = X
# Forward propagation.
# Inside the perceptron, Step 2.
layer1 = sigmoid(np.dot(layer0, W1))
layer2 = sigmoid(np.dot(layer1, W2))
# Back propagation (Y -> layer2)
# How much did we miss in the predictions?
cost_error = mse(layer2, Y)
cost_delta = mse_derivative(layer2, Y)
#print(layer2_error)
# In what direction is the target value?
# Were we really close? If so, don't change too much.
layer2_error = np.dot(cost_delta, cost_error)
layer2_delta = layer2_error * sigmoid_derivative(layer2)
# Back propagation (layer2 -> layer1)
# How much did each layer1 value contribute to the layer2 error (according to the weights)?
layer1_error = np.dot(layer2_delta, W2.T)
layer1_delta = layer1_error * sigmoid_derivative(layer1)
# update weights
W2 += - learning_rate * np.dot(layer1.T, layer2_delta)
W1 += - learning_rate * np.dot(layer0.T, layer1_delta)
It seemed to train and learn the XOR...
But now the question begets, is the layer2_error and layer2_delta computed correctly, i.e. is the following part of the code correct?
# How much did we miss in the predictions?
cost_error = mse(layer2, Y)
cost_delta = mse_derivative(layer2, Y)
#print(layer2_error)
# In what direction is the target value?
# Were we really close? If so, don't change too much.
layer2_error = np.dot(cost_delta, cost_error)
layer2_delta = layer2_error * sigmoid_derivative(layer2)
Is it correct to do a dot product on the cost_delta and cost_error for the layer2_error? Or would layer2_error just be equals to cost_delta?
I.e.
# How much did we miss in the predictions?
cost_error = mse(layer2, Y)
cost_delta = mse_derivative(layer2, Y)
#print(layer2_error)
# In what direction is the target value?
# Were we really close? If so, don't change too much.
layer2_error = cost_delta
layer2_delta = layer2_error * sigmoid_derivative(layer2)
Yes, it is correct to multiply the residuals (cost_error) with the delta values when we update the weights.
However, it doesn't really matter whether do dot product or not since it cost_error is a scalar. So, a simple multiplication is enough. But, we definitely have to multiply the gradient of the cost function because that's where we start our backprop (i.e. it's the entry point for backward pass).
Also, the below function can be simplified:
def mse(predicted, truth):
return 0.5 * np.sum(np.square(predicted - truth)).mean()
as
def mse(predicted, truth):
return 0.5 * np.mean(np.square(predicted - truth))
Below I attached 4 pictures with error as a picture.
Generally, I'm training my neural network ( having a 2, 3, 1 architecture ) that consists of two input neurons in the input layer, 3 neurons in my hidden layer and 1 output neuron in my output layer.
So, I trained my network using back propagation and I am having small error ( which is specified in the picture ).
Can someone help me with that please.
Error: shapes (200,200) and (1,3) not aligned: 200 (dim 1) != 1 (dim 0)
import numpy as np
import random
# Generating training data set according to the function y=x^2+y^2
input1_train = np.random.uniform(low=-1, high=1, size=(200,))
input2_train = np.random.uniform(low=-1, high=1, size=(200,))
input1_sq_train= input1_train **2
input2_sq_train= input2_train **2
input_merge= np.column_stack((input1_train,input2_train))
# normalized input data
input_merge= input_merge / np.amax(input_merge, axis=0)
# output of the training data
y_output_train= input1_sq_train + input2_sq_train
# normalized output data
y_output_train= y_output_train / 100
# Generating test data set according to the function y=x^2+y^2
input1_test = np.random.uniform(low=-1, high=1, size=(100,))
input2_test = np.random.uniform(low=-1, high=1, size=(100,))
input1_sq_test= input1_test **2
input2_sq_test= input2_test **2
y_output_test= input1_sq_test + input2_sq_test
# Merging two inputs of testing data into an one matrix
input_merge1= np.column_stack((input1_test,input2_test))
# normalized input test data
input_merge1=input_merge1 / np.amax(input_merge1, axis=0)
# normalized output test data
y_output_test= y_output_test / 100
# Generating validation data set according to the function y=x^2+y^2
input1_validation = np.random.uniform(low=-1, high=1, size=(50,))
input2_validation = np.random.uniform(low=-1, high=1, size=(50,))
input1_sq_validation= input1_validation **2
input2_sq_validation= input2_validation **2
input_merge2= np.column_stack((input1_validation,input2_validation))
# normalized input validation data
input_merge2= input_merge2 / np.amax(input_merge2, axis=0)
y_output_validation= input1_sq_validation + input2_sq_validation
# normalized output validation data
y_output_validation= y_output_validation / 100
class Neural_Network(object):
def __init__(self):
# parameters
self.inputSize = 2
self.outputSize = 1
self.hiddenSize = 3
# weights
self.W1 = np.random.randn(self.inputSize, self.hiddenSize) # (3x2)
# weight matrix from input to hidden layer
self.W2 = np.random.randn(self.hiddenSize, self.outputSize) # (3x1)
# weight matrix from hidden to output layer
def forward(self, input_merge):
# forward propagation through our network
self.z = np.dot(input_merge, self.W1) # dot product of X (input) and first set of 3x2 weights
self.z2 = self.sigmoid(self.z) # activation function
self.z3 = np.dot(self.z2, self.W2) # dot product of hidden layer (z2)
# and second set of 3x1 weights
o = self.sigmoid(self.z3) # final activation function
return o
def costFunction(self, input_merge, y_output_train):
# Compute cost for given X,y, use weights already stored in class.
self.o = self.forward(input_merge)
J = 0.5*sum((y_output_train-self.yHat)**2)
return J
def costFunctionPrime(self, input_merge, y_output_train):
# Compute derivative with respect to W and W2 for a given X and y:
self.o = self.forward(input_merge)
delta3 = np.multiply(-(y_output_train-self.yHat),
self.sigmoidPrime(self.z3))
dJdW2 = np.dot(self.a2.T, delta3)
delta2 = np.dot(delta3, self.W2.T)*self.sigmoidPrime(self.z2)
dJdW1 = np.dot(input_merge.T, delta2)
return dJdW1, dJdW2
def sigmoid(self, s):
# activation function
return 1/(1+np.exp(-s))
def sigmoidPrime(self, s):
# derivative of sigmoid
return s * (1 - s)
def backward(self, input_merge, y_output_train, o):
# backward propgate through the network
self.o_error = y_output_train - o # error in output
self.o_delta = self.o_error*self.sigmoidPrime(o) # applying derivative of sigmoid to error
self.z2_error = self.o_delta.dot(self.W2.T) # z2 error: how much our hidden layer weights contributed to output error
self.z2_delta = self.z2_error*self.sigmoidPrime(self.z2) # applying derivative of sigmoid to z2 error
self.W1 += input_merge.T.dot(self.z2_delta) # adjusting first set (input --> hidden) weights
self.W2 += self.z2.T.dot(self.o_delta) # adjusting second set (hidden --> output) weights
def train (self, input_merge, y_output_train):
o = self.forward(input_merge)
self.backward(input_merge, y_output_train, o)
NN = Neural_Network()
for i in range(1000): # trains the NN 1,000 times
# print ( "Actual Output for training data: \n" + str(y_output_train))
# print ("Predicted Output for training data: \n" + str(NN.forward(input_merge)))
print ( "Loss for training: \n"
+ str( np.mean( np.square( y_output_train
- NN.forward( input_merge )
)
)
)
) # mean sum squared loss
NN.train(input_merge, y_output_train)
# NN.test(input_merge1,y_output_test)
# NN.validation(input_merge2,y_output_validation)
"having small error" is actually a major issue on mat/vec-dimensions:
so, first, it is a fair practice to post MCVE-based formulation of StackOverflow presented problems.
Here, that would mean to also copy the complete Error-Traceback, including the row numbers, where the Traceback has been thrown. Ok, you will get it right next time.
Your problem is not a small error -- your code is principally wrong, as it tries ( at an unknown location ) to process a pair of arrays, that do not match in shape for a yet unknown operation ( it just seems that a .multiply() is the right suspect, but not sure, where it could get called, as there is no clear request to ask for a .costFunctionPrime() method ).
Nevertheless, an attempt was done, somewhere, to process the pair of matrix/vector arrays,
one, being [200,200], the other, being [1,3] simply do not make their processing possible.
So, the error is in your code / syntax. Check it, possibly using a pre-printed shape-checks:
def aFormatSHAPE( anArray ):
return "[{0: >4d},{1: >4d}]".format( anArray.shape[0],
anArray.shape[1]
)
def aHelperPrintSHAPE( anArray1, anArray2 ):
try:
print( "CHK:{0:}-(op)-{1:}".format( aFormatSHAPE( anArray1 ),
aFormatSHAPE( anArray2 )
)
)
except:
pass
return
Once you repair your code so that it meets all the common matrix-vector algebra rules ( on how additions, subtractions, multiplications, dot-products are processed on arrays/vectors ), then your small error is solved.
You should never see anything like:
CHK:[200,200]-(op)-[1,3]
It seems to me your matrix dimensions don't fit. You cannot multiply (200,200) with (1,3). No. of columns of first matrix must match no. of rows of second matrix in simple terms. Hope this helps.
I've created a neural network to estimate the sin(x) function for an input x. The network has 21 output neurons (representing numbers -1.0, -0.9, ..., 0.9, 1.0) with numpy that does not learn, as I think I implemented the neuron architecture incorrectly when I defined the feedforward mechanism.
When I execute the code, the amount of test data it estimates correctly sits around 48/1000. This happens to be the average data point count per category if you split 1000 test data points between 21 categories. Looking at the network output, you can see that the network seems to just start picking a single output value for every input. For example, it may pick -0.5 as the estimate for y regardless of the x you give it. Where did I go wrong here? This is my first network. Thank you!
import random
import numpy as np
import math
class Network(object):
def __init__(self,inputLayerSize,hiddenLayerSize,outputLayerSize):
#Create weight vector arrays to represent each layer size and initialize indices randomly on a Gaussian distribution.
self.layer1 = np.random.randn(hiddenLayerSize,inputLayerSize)
self.layer1_activations = np.zeros((hiddenLayerSize, 1))
self.layer2 = np.random.randn(outputLayerSize,hiddenLayerSize)
self.layer2_activations = np.zeros((outputLayerSize, 1))
self.outputLayerSize = outputLayerSize
self.inputLayerSize = inputLayerSize
self.hiddenLayerSize = hiddenLayerSize
# print(self.layer1)
# print()
# print(self.layer2)
# self.weights = [np.random.randn(y,x)
# for x, y in zip(sizes[:-1], sizes[1:])]
def feedforward(self, network_input):
#Propogate forward through network as if doing this by hand.
#first layer's output activations:
for neuron in range(self.hiddenLayerSize):
self.layer1_activations[neuron] = 1/(1+np.exp(network_input * self.layer1[neuron]))
#second layer's output activations use layer1's activations as input:
for neuron in range(self.outputLayerSize):
for weight in range(self.hiddenLayerSize):
self.layer2_activations[neuron] += self.layer1_activations[weight]*self.layer2[neuron][weight]
self.layer2_activations[neuron] = 1/(1+np.exp(self.layer2_activations[neuron]))
#convert layer 2 activation numbers to a single output. The neuron (weight vector) with highest activation will be output.
outputs = [x / 10 for x in range(-int((self.outputLayerSize/2)), int((self.outputLayerSize/2))+1, 1)] #range(-10, 11, 1)
return(outputs[np.argmax(self.layer2_activations)])
def train(self, training_pairs, epochs, minibatchsize, learn_rate):
#apply gradient descent
test_data = build_sinx_data(1000)
for epoch in range(epochs):
random.shuffle(training_pairs)
minibatches = [training_pairs[k:k + minibatchsize] for k in range(0, len(training_pairs), minibatchsize)]
for minibatch in minibatches:
loss = 0 #calculate loss for each minibatch
#Begin training
for x, y in minibatch:
network_output = self.feedforward(x)
loss += (network_output - y) ** 2
#adjust weights by abs(loss)*sigmoid(network_output)*(1-sigmoid(network_output)*learn_rate
loss /= (2*len(minibatch))
adjustWeights = loss*(1/(1+np.exp(-network_output)))*(1-(1/(1+np.exp(-network_output))))*learn_rate
self.layer1 += adjustWeights
#print(adjustWeights)
self.layer2 += adjustWeights
#when line 63 placed here, results did not improve during minibatch.
print("Epoch {0}: {1}/{2} correct".format(epoch, self.evaluate(test_data), len(test_data)))
print("Training Complete")
def evaluate(self, test_data):
"""
Returns number of test inputs which network evaluates correctly.
The ouput assumed to be neuron in output layer with highest activation
:param test_data: test data set identical in form to train data set.
:return: integer sum
"""
correct = 0
for x, y in test_data:
output = self.feedforward(x)
if output == y:
correct+=1
return(correct)
def build_sinx_data(data_points):
"""
Creates a list of tuples (x value, expected y value) for Sin(x) function.
:param data_points: number of desired data points
:return: list of tuples (x value, expected y value
"""
x_vals = []
y_vals = []
for i in range(data_points):
#parameter of randint signifies range of x values to be used*10
x_vals.append(random.randint(-2000,2000)/10)
y_vals.append(round(math.sin(x_vals[i]),1))
return (list(zip(x_vals,y_vals)))
# training_pairs, epochs, minibatchsize, learn_rate
sinx_test = Network(1,21,21)
print(sinx_test.feedforward(10))
sinx_test.train(build_sinx_data(600),20,10,2)
print(sinx_test.feedforward(10))
I didn't examine thoroughly all of your code, but some issues are clearly visible:
* operator doesn't perform matrix multiplication in numpy, you have to use numpy.dot. This affects, for instance, these lines: network_input * self.layer1[neuron], self.layer1_activations[weight]*self.layer2[neuron][weight], etc.
Seems like you are solving your problem via classification (selecting 1 out of 21 classes), but using L2 loss. This is somewhat mixed up. You have two options: either stick to classification and use a cross entropy loss function, or perform regression (i.e. predict the numeric value) with L2 loss.
You should definitely extract sigmoid function to avoid writing the same expression all over again:
def sigmoid(z):
return 1 / (1 + np.exp(-z))
def sigmoid_derivative(x):
return sigmoid(x) * (1 - sigmoid(x))
You perform the same update of self.layer1 and self.layer2, which clearly wrong. Take some time analyzing how exactly backpropagation works.
I edited how my loss function was integrated into my function and also correctly implemented gradient descent. I also removed the use of mini-batches and simplified what my network was trying to do. I now have a network which attempts to classify something as even or odd.
Some extremely helpful guides I used to fix things up:
Chapter 1 and 2 of Neural Networks and Deep Learning, by Michael Nielsen, available for free at http://neuralnetworksanddeeplearning.com/chap1.html . This book gives thorough explanations for how Neural Nets work, including breakdowns of the math behind their execution.
Backpropagation from the Beginning, by Erik Hallström, linked by Maxim. https://medium.com/#erikhallstrm/backpropagation-from-the-beginning-77356edf427d
. Not as thorough as the above guide, but I kept both open concurrently, as this guide is more to the point about what is important and how to apply the mathematical formulas that are thoroughly explained in Nielsen's book.
How to build a simple neural network in 9 lines of Python code https://medium.com/technology-invention-and-more/how-to-build-a-simple-neural-network-in-9-lines-of-python-code-cc8f23647ca1
. A useful and fast introduction to some neural networking basics.
Here is my (now functioning) code:
import random
import numpy as np
import scipy
import math
class Network(object):
def __init__(self,inputLayerSize,hiddenLayerSize,outputLayerSize):
#Layers represented both by their weights array and activation and inputsums vectors.
self.layer1 = np.random.randn(hiddenLayerSize,inputLayerSize)
self.layer2 = np.random.randn(outputLayerSize,hiddenLayerSize)
self.layer1_activations = np.zeros((hiddenLayerSize, 1))
self.layer2_activations = np.zeros((outputLayerSize, 1))
self.layer1_inputsums = np.zeros((hiddenLayerSize, 1))
self.layer2_inputsums = np.zeros((outputLayerSize, 1))
self.layer1_errorsignals = np.zeros((hiddenLayerSize, 1))
self.layer2_errorsignals = np.zeros((outputLayerSize, 1))
self.layer1_deltaw = np.zeros((hiddenLayerSize, inputLayerSize))
self.layer2_deltaw = np.zeros((outputLayerSize, hiddenLayerSize))
self.outputLayerSize = outputLayerSize
self.inputLayerSize = inputLayerSize
self.hiddenLayerSize = hiddenLayerSize
print()
print(self.layer1)
print()
print(self.layer2)
print()
# self.weights = [np.random.randn(y,x)
# for x, y in zip(sizes[:-1], sizes[1:])]
def feedforward(self, network_input):
#Calculate inputsum and and activations for each neuron in the first layer
for neuron in range(self.hiddenLayerSize):
self.layer1_inputsums[neuron] = network_input * self.layer1[neuron]
self.layer1_activations[neuron] = self.sigmoid(self.layer1_inputsums[neuron])
# Calculate inputsum and and activations for each neuron in the second layer. Notice that each neuron in the second layer represented by
# weights vector, consisting of all weights leading out of the kth neuron in (l-1) layer to the jth neuron in layer l.
self.layer2_inputsums = np.zeros((self.outputLayerSize, 1))
for neuron in range(self.outputLayerSize):
for weight in range(self.hiddenLayerSize):
self.layer2_inputsums[neuron] += self.layer1_activations[weight]*self.layer2[neuron][weight]
self.layer2_activations[neuron] = self.sigmoid(self.layer2_inputsums[neuron])
return self.layer2_activations
def interpreted_output(self, network_input):
#convert layer 2 activation numbers to a single output. The neuron (weight vector) with highest activation will be output.
self.feedforward(network_input)
outputs = [x / 10 for x in range(-int((self.outputLayerSize/2)), int((self.outputLayerSize/2))+1, 1)] #range(-10, 11, 1)
return(outputs[np.argmax(self.layer2_activations)])
# def build_expected_output(self, training_data):
# #Views expected output number y for each x to generate an expected output vector from the network
# index=0
# for pair in training_data:
# expected_output_vector = np.zeros((self.outputLayerSize,1))
# x = training_data[0]
# y = training_data[1]
# for i in range(-int((self.outputLayerSize / 2)), int((self.outputLayerSize / 2)) + 1, 1):
# if y == i / 10:
# expected_output_vector[i] = 1
# #expect the target category to be a 1.
# break
# training_data[index][1] = expected_output_vector
# index+=1
# return training_data
def train(self, training_data, learn_rate):
self.backpropagate(training_data, learn_rate)
def backpropagate(self, train_data, learn_rate):
#Perform for each x,y pair.
for datapair in range(len(train_data)):
x = train_data[datapair][0]
y = train_data[datapair][1]
self.feedforward(x)
# print("l2a " + str(self.layer2_activations))
# print("l1a " + str(self.layer1_activations))
# print("l2 " + str(self.layer2))
# print("l1 " + str(self.layer1))
for neuron in range(self.outputLayerSize):
#Calculate first error equation for error signals of output layer neurons
self.layer2_errorsignals[neuron] = (self.layer2_activations[neuron] - y[neuron]) * self.sigmoid_prime(self.layer2_inputsums[neuron])
#Use recursive formula to calculate error signals of hidden layer neurons
self.layer1_errorsignals = np.multiply(np.array(np.matrix(self.layer2.T) * np.matrix(self.layer2_errorsignals)) , self.sigmoid_prime(self.layer1_inputsums))
#print(self.layer1_errorsignals)
# for neuron in range(self.hiddenLayerSize):
# #Use recursive formula to calculate error signals of hidden layer neurons
# self.layer1_errorsignals[neuron] = np.multiply(self.layer2[neuron].T,self.layer2_errorsignals[neuron]) * self.sigmoid_prime(self.layer1_inputsums[neuron])
#Partial derivative of C with respect to weight for connection from kth neuron in (l-1)th layer to jth neuron in lth layer is
#(jth error signal in lth layer) * (kth activation in (l-1)th layer.)
#Update all weights for network at each iteration of a training pair.
#Update weights in second layer
for neuron in range(self.outputLayerSize):
for weight in range(self.hiddenLayerSize):
self.layer2_deltaw[neuron][weight] = self.layer2_errorsignals[neuron]*self.layer1_activations[weight]*(-learn_rate)
self.layer2 += self.layer2_deltaw
#Update weights in first layer
for neuron in range(self.hiddenLayerSize):
self.layer1_deltaw[neuron] = self.layer1_errorsignals[neuron]*(x)*(-learn_rate)
self.layer1 += self.layer1_deltaw
#Comment/Uncomment to enable error evaluation.
#print("Epoch {0}: Error: {1}".format(datapair, self.evaluate(test_data)))
# print("l2a " + str(self.layer2_activations))
# print("l1a " + str(self.layer1_activations))
# print("l1 " + str(self.layer1))
# print("l2 " + str(self.layer2))
def evaluate(self, test_data):
error = 0
for x, y in test_data:
#x is integer, y is single element np.array
output = self.feedforward(x)
error += y - output
return error
#eval function for sin(x)
# def evaluate(self, test_data):
# """
# Returns number of test inputs which network evaluates correctly.
# The ouput assumed to be neuron in output layer with highest activation
# :param test_data: test data set identical in form to train data set.
# :return: integer sum
# """
# correct = 0
# for x, y in test_data:
# outputs = [x / 10 for x in range(-int((self.outputLayerSize / 2)), int((self.outputLayerSize / 2)) + 1,
# 1)] # range(-10, 11, 1)
# newy = outputs[np.argmax(y)]
# output = self.interpreted_output(x)
# #print("output: " + str(output))
# if output == newy:
# correct+=1
# return(correct)
def sigmoid(self, z):
return 1 / (1 + np.exp(-z))
def sigmoid_prime(self, z):
return (1 - self.sigmoid(z)) * self.sigmoid(z)
def build_simple_data(data_points):
x_vals = []
y_vals = []
for each in range(data_points):
x = random.randint(-3,3)
expected_output_vector = np.zeros((1, 1))
if x > 0:
expected_output_vector[[0]] = 1
else:
expected_output_vector[[0]] = 0
x_vals.append(x)
y_vals.append(expected_output_vector)
print(list(zip(x_vals,y_vals)))
print()
return (list(zip(x_vals,y_vals)))
simpleNet = Network(1, 3, 1)
# print("Pretest")
# print(simpleNet.feedforward(-3))
# print(simpleNet.feedforward(10))
# init_weights_l1 = simpleNet.layer1
# init_weights_l2 = simpleNet.layer2
# simpleNet.train(build_simple_data(10000),.1)
# #sometimes Error converges to 0, sometimes error converges to 10.
# print("Initial Weights:")
# print(init_weights_l1)
# print(init_weights_l2)
# print("Final Weights")
# print(simpleNet.layer1)
# print(simpleNet.layer2)
# print("Post-test")
# print(simpleNet.feedforward(-3))
# print(simpleNet.feedforward(10))
def test_network(iterations,net,training_points):
"""
Casually evaluates pre and post test
:param iterations: number of trials to be run
:param net: name of network to evaluate.
;param training_points: size of training data to be used
:return: four 1x1 arrays.
"""
pretest_negative = 0
pretest_positive = 0
posttest_negative = 0
posttest_positive = 0
for each in range(iterations):
pretest_negative += net.feedforward(-10)
pretest_positive += net.feedforward(10)
net.train(build_simple_data(training_points),.1)
for each in range(iterations):
posttest_negative += net.feedforward(-10)
posttest_positive += net.feedforward(10)
return(pretest_negative/iterations, pretest_positive/iterations, posttest_negative/iterations, posttest_positive/iterations)
print(test_network(10000, simpleNet, 10000))
While much differs between this code and the code posted in the OP, there is a particular difference that is interesting. In the original feedforward method notice
#second layer's output activations use layer1's activations as input:
for neuron in range(self.outputLayerSize):
for weight in range(self.hiddenLayerSize):
self.layer2_activations[neuron] += self.layer1_activations[weight]*self.layer2[neuron][weight]
self.layer2_activations[neuron] = 1/(1+np.exp(self.layer2_activations[neuron]))
The line
self.layer2_activations[neuron] += self.layer1_activations[weight]*self.layer2[neuron][weight]
Resembles
self.layer2_inputsums[neuron] += self.layer1_activations[weight]*self.layer2[neuron][weight]
In the updated code. This line performs the dot product between each weight vector and each input vector (the activations from layer 1) to arrive at the input_sum for a neuron, commonly referred to as z (think sigmoid(z)). In my network, the derivative of the sigmoid function, sigmoid_prime, is used to calculate the gradient of the cost function with respect to all the weights. By multiplying sigmoid_prime(z) * network error between actual and expected output. If z is very big (and positive), the neuron will have an activation value very close to 1. That means that the network is confident that that neuron should be activating. The same is true if z is very negative. The network, then, doesn't want to radically adjust weights that it is happy with, so the scale of the change in each weight for a neuron is given by the gradient of sigmoid(z), sigmoid_prime(z). Very large z means very small gradient and very small change applied to weights (the gradient of sigmoid is maximized at z = 0, when the network is unconfident about how a neuron should be categorized and when the activation for that neuron is 0.5).
Since I was continually adding on to each neuron's input_sum (z) and never resetting the value for new inputs of dot(weights, activations), the value for z kept growing, continually slowing the rate of change for the weights until weight modification grew to a standstill. I added the following line to cope with this:
self.layer2_inputsums = np.zeros((self.outputLayerSize, 1))
The new posted network can be copy and pasted into an editor and executed so long as you have the numpy module installed. The final line of output to print will be a list of 4 arrays representing final network output. The first two are the pretest values for a negative and positive input, respectively. These should be random. The second two are post-test values to determine how well the network classifies as positive and negative number. A number near 0 denotes negative, near 1 denotes positive.
I have implemented and trained a neural network with Theano of k binary inputs (0,1), one hidden layer and one unit in the output layer. Once it has been trained I want to obtain inputs that maximizes the output (e.g. x which makes unit of output layer closest to 1). So far I haven't found an implementation of it, so I am trying the following approach:
Train network => obtain trained weights (theta1, theta2)
Define the neural network function with x as input and trained theta1, theta2 as fixed parameters. That is: f(x) = sigmoid( theta1*(sigmoid (theta2*x ))). This function takes x and with given trained weights (theta1, theta2) gives output between 0 and 1.
Apply gradient descent w.r.t. x on the neural network function f(x) and obtain x that maximizes f(x) with theta1 and theta2 given.
For these I have implemented the following code with a toy example (k = 2). Based on the tutorial on http://outlace.com/Beginner-Tutorial-Theano/ but changed vector y, so that there is only one combination of inputs that gives f(x) ~ 1 which is x = [0, 1].
Edit1: As suggested optimizer was set to None and bias unit was fixed to 1.
Step 1: Train neural network. This runs well and with out error.
import os
os.environ["THEANO_FLAGS"] = "optimizer=None"
import theano
import theano.tensor as T
import theano.tensor.nnet as nnet
import numpy as np
x = T.dvector()
y = T.dscalar()
def layer(x, w):
b = np.array([1], dtype=theano.config.floatX)
new_x = T.concatenate([x, b])
m = T.dot(w.T, new_x) #theta1: 3x3 * x: 3x1 = 3x1 ;;; theta2: 1x4 * 4x1
h = nnet.sigmoid(m)
return h
def grad_desc(cost, theta):
alpha = 0.1 #learning rate
return theta - (alpha * T.grad(cost, wrt=theta))
in_units = 2
hid_units = 3
out_units = 1
theta1 = theano.shared(np.array(np.random.rand(in_units + 1, hid_units), dtype=theano.config.floatX)) # randomly initialize
theta2 = theano.shared(np.array(np.random.rand(hid_units + 1, out_units), dtype=theano.config.floatX))
hid1 = layer(x, theta1) #hidden layer
out1 = T.sum(layer(hid1, theta2)) #output layer
fc = (out1 - y)**2 #cost expression
cost = theano.function(inputs=[x, y], outputs=fc, updates=[
(theta1, grad_desc(fc, theta1)),
(theta2, grad_desc(fc, theta2))])
run_forward = theano.function(inputs=[x], outputs=out1)
inputs = np.array([[0,1],[1,0],[1,1],[0,0]]).reshape(4,2) #training data X
exp_y = np.array([1, 0, 0, 0]) #training data Y
cur_cost = 0
for i in range(5000):
for k in range(len(inputs)):
cur_cost = cost(inputs[k], exp_y[k]) #call our Theano-compiled cost function, it will auto update weights
print(run_forward([0,1]))
Output of run forward for [0,1] is: 0.968905860574.
We can also get values of weights with theta1.get_value() and theta2.get_value()
Step 2: Define neural network function f(x). Trained weights (theta1, theta2) are constant parameters of this function.
Things get a little trickier here because of the bias unit, which is part of he vector of inputs x. To do this I concatenate b and x. But the code now runs well.
b = np.array([[1]], dtype=theano.config.floatX)
#b_sh = theano.shared(np.array([[1]], dtype=theano.config.floatX))
rand_init = np.random.rand(in_units, 1)
rand_init[0] = 1
x_sh = theano.shared(np.array(rand_init, dtype=theano.config.floatX))
th1 = T.dmatrix()
th2 = T.dmatrix()
nn_hid = T.nnet.sigmoid( T.dot(th1, T.concatenate([x_sh, b])) )
nn_predict = T.sum( T.nnet.sigmoid( T.dot(th2, T.concatenate([nn_hid, b]))))
Step 3:
Problem is now in gradient descent as is not limited to values between 0 and 1.
fc2 = (nn_predict - 1)**2
cost3 = theano.function(inputs=[th1, th2], outputs=fc2, updates=[
(x_sh, grad_desc(fc2, x_sh))])
run_forward = theano.function(inputs=[th1, th2], outputs=nn_predict)
cur_cost = 0
for i in range(10000):
cur_cost = cost3(theta1.get_value().T, theta2.get_value().T) #call our Theano-compiled cost function, it will auto update weights
if i % 500 == 0: #only print the cost every 500 epochs/iterations (to save space)
print('Cost: %s' % (cur_cost,))
print x_sh.get_value()
The last iteration prints:
Cost: 0.000220317356533
[[-0.11492753]
[ 1.99729555]]
Furthermore input 1 keeps becoming more negative and input 2 increases, while the optimal solution is [0, 1]. How can this be fixed?
You are adding b=[1] via broadcasting rules as opposed to concatenating it. Also, once you concatenate it, your x_sh has one dimension to many which is why the error occurs at nn_predict and not nn_hid