The document outlines the architecture and calculations involved in training a neural network using backpropagation. It describes a simple case study with two inputs, hidden neurons, and output neurons, detailing the process of feeding inputs through the network and updating weights to minimize error. After multiple iterations, the network significantly reduces its error in predicting the target outputs from the given inputs.
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
0 ratings0% found this document useful (0 votes)
19 views24 pages
ANN Calculations
The document outlines the architecture and calculations involved in training a neural network using backpropagation. It describes a simple case study with two inputs, hidden neurons, and output neurons, detailing the process of feeding inputs through the network and updating weights to minimize error. After multiple iterations, the network significantly reduces its error in predicting the target outputs from the given inputs.
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 24
ANN calculations
Background calculation with simple case study
ANN Architecture
• We use a neural network with
two inputs, two hidden neurons, two output neurons. Additionally, the hidden and output neurons will include a bias. ANN Architecture
In order to have some numbers to work
with, here are the initial weights, the biases, and training inputs/outputs.
The goal of backpropagation is to
optimize the weights so that the neural network can learn how to correctly map arbitrary inputs to outputs.
For the rest of this tutorial we’re going to
work with a single training set: given inputs 0.05 and 0.10, we want the neural network to output 0.01 and 0.99. ANN Calculation
• To begin, lets see what the
neural network currently predicts given the weights and biases above and inputs of 0.05 and 0.10. • To do this we’ll feed those inputs forward though the network. ANN Calculation
• We figure out the total net
input to each hidden layer neuron, squash the total net input using an activation function (here we use the logistic function), then repeat the process with the output layer neurons. • Total net input is also referred to as just net input ANN Calculation ANN Calculation Calculating the Total Error The Backwards Pass
• Our goal with
backpropagation is to update each of the weights in the network so that they cause the actual output to be closer the target output, thereby minimizing the error for each output neuron and the network as a whole. The Backwards Pass : Output Layer The Backwards Pass : Output Layer
• First, how much does the total
error change with respect to the output? The Backwards Pass : Output Layer The Backwards Pass : Output Layer The Backwards Pass : Output Layer The Backwards Pass : Output Layer The Backwards Pass : Output Layer The Backwards Pass : Hidden Layer The Backwards Pass : Hidden Layer The Backwards Pass : Hidden Layer The Backwards Pass : Hidden Layer The Backwards Pass : Hidden Layer The Backwards Pass : Hidden Layer The Backwards Pass : Hidden Layer Update Weights Finally, we’ve updated all of our weights! When we fed forward the 0.05 and 0.1 inputs originally, the error on the network was 0.298371109.
After this first round of backpropagation, the
total error is now down to 0.291027924.
It might not seem like much, but after
repeating this process 10,000 times, for example, the error plummets to 0.0000351085.
At this point, when we feed forward 0.05 and
0.1, the two outputs neurons generate 0.015912196 (vs 0.01 target) and