COS711 Assignment 1

Due date: 4 September 2022, at 23h30

1 General instructions

This assignment is theoretical, and will test your understanding of the backpropagation algorithm. You have to submit a single pdf document containing your answers to the questions provided. Note: the assignment is designed to test your ability to derive the weight update equations for arbitrary loss and activation functions. Thus, you will loose marks by skipping over steps. Make sure your derivations are readable, notation is correct, and the steps (including simplifications) are clear.

The report will be checked for plagiarism using Turnitin, and should be submitted through the ClickUp system. You are advised but not required to typeset your report in LaTeX.

2 Deriving backpropagation (25 marks)

A feed-forward neural network is set up to have an input layer of size I, a hidden layer of size H, and an output layer of size O. The following activation functions are employed in the neurons on each layer:

• Input layer: identity, f(x) = x

• Hidden layer: Softplus, f(x) = ln(1 + ex)

• Output layer: Modified Elliott,

Hidden and output units are summation units, i.e. x in the activation functions above refers to the net input signal, thus the output signal of a neuron j is yj = f(netj) = f(Pwkjyk). Bias signal is sent to all hidden, as well as all output units. Assume the objective function E is used, defined for a single input data pattern as:

where yi is the output of the i-th output unit, ti is the target output of the i-th output unit, ln refers to natural logarithm, s1 and s2 are scalar values such that s1 + s2 = 1, maxE1 and maxE2 are the maximum values produced by E1 and E2 over the data set before training, respectively.

Answer the questions below:

1. Derive the update rule for the non-bias weights between the hidden and the output layer. Showall steps, including simplifications. (10 marks)

1

2. Derive the update rule for the non-bias weights between the input and the hidden layer. Showall steps, including simplifications. (10 marks)

3. Will the bias weight update rules differ from the non-bias weight update rules? Derive theupdate rule for the bias weights associated with the hidden layer. Show your working. (5 marks)

2

Due date: 4 September 2022, at 23h30

1 General instructions

This assignment is theoretical, and will test your understanding of the backpropagation algorithm. You have to submit a single pdf document containing your answers to the questions provided. Note: the assignment is designed to test your ability to derive the weight update equations for arbitrary loss and activation functions. Thus, you will loose marks by skipping over steps. Make sure your derivations are readable, notation is correct, and the steps (including simplifications) are clear.

The report will be checked for plagiarism using Turnitin, and should be submitted through the ClickUp system. You are advised but not required to typeset your report in LaTeX.

2 Deriving backpropagation (25 marks)

A feed-forward neural network is set up to have an input layer of size I, a hidden layer of size H, and an output layer of size O. The following activation functions are employed in the neurons on each layer:

• Input layer: identity, f(x) = x

• Hidden layer: Softplus, f(x) = ln(1 + ex)

• Output layer: Modified Elliott,

Hidden and output units are summation units, i.e. x in the activation functions above refers to the net input signal, thus the output signal of a neuron j is yj = f(netj) = f(Pwkjyk). Bias signal is sent to all hidden, as well as all output units. Assume the objective function E is used, defined for a single input data pattern as:

where yi is the output of the i-th output unit, ti is the target output of the i-th output unit, ln refers to natural logarithm, s1 and s2 are scalar values such that s1 + s2 = 1, maxE1 and maxE2 are the maximum values produced by E1 and E2 over the data set before training, respectively.

Answer the questions below:

1. Derive the update rule for the non-bias weights between the hidden and the output layer. Showall steps, including simplifications. (10 marks)

1

2. Derive the update rule for the non-bias weights between the input and the hidden layer. Showall steps, including simplifications. (10 marks)

3. Will the bias weight update rules differ from the non-bias weight update rules? Derive theupdate rule for the bias weights associated with the hidden layer. Show your working. (5 marks)

2

People places and social DifferencesWrite a Photographic essayTopic: What are the benefits and challenges of multiculturalismChoose one Suburb in SydneyEg Blacktown with some provided photosThen write...Mat 101Task 1Find the limit values:Task 2Find all vertical and horizontal asymptotes toTask 3Find the sums: ( b is to infinity)Task 4The concentration of an algae in the fjord varies periodically with...28 September 2022 at 12:39 amUnit name: Behavioural science = APA 7th edition Refereeing stylePsychology Research Report1,700 wordsTopic is to focus on emotions in general Different findings between anger...the seven segment display is not coming up in the circuit please correct the circuit and resend the proteus file with the working circuitI need it done as soon as possible pleasei just want to know how to apply the model using PML package in RIFN561: Enterprise Systems Lifecycle ManagementAssessment Task 2Assessment Task 2Task overviewAssessment name: Request for Proposal (RFP)Task description: The objective for this assignment is to build...**Show All Questions**