COMP24111: Machine Learning and Optimization (Part I) Dr. Tingting - - PowerPoint PPT Presentation

COMP24111: Machine Learning and Optimization (Part I)

• Dr. Tingting Mu

Email: tingting.mu@manchester.ac.uk

Exam Information

• Exam on week 1-5 content includes:

– 15 MCQ questions (one mark each question). – 15 marks of written questions.

• Revision material:

– Lecture notes (Comp24111 website). – Podcast (Blackboard). – Comments in annotated lecture notes (Blackboard). – Exercises and MCQ practices with solution (Comp24111 website). – Mock exam paper with solution (Comp24111 website). – Past exam papers (for taught parts).

1

Examination Content and Methods: Chapter 1

2

Content Assessing Method

Basic ideas of machine learning. MCQ Typical learning types (unsupervised, supervised, reinforcement learning). MCQ k-NN classifier:

• K-NN classification rules (core idea and pseudo code).
• k-NN behaviour vs. neighbour number and training

sample size.

• Usage of k-NN (e.g., suitable for both linear and

nonlinear classification). MCQ, written questions Basic machine learning experiment settings (training, testing, classification accuracy and error rate ) MCQ

Examination Content and Methods: Chapter 2

3

Content Assessing Method

Definition of classification and regression tasks. MCQ Basic machine learning ingredients (model, error function, learning). MCQ Linear model based on least squares solution:

• Model formulation and model parameter, sum-of-squares error.
• Derive the best setting of the model parameter for cases with one

input variable and one output variable (e.g., MAIP example).

• Usage of linear model for regression and classification.
• Basic idea of regularised least squares model.

MCQ and written questions Basic ideas of gradient descent, stochastic gradient descent, and mini-batch gradient descent. MCQ

Examination Content and Methods: Chapter 3

4

Content Assessing Method

Definition of likelihood and maximum likelihood estimator. MCQ Logistic regression model:

• Basic idea of the model.
• Training by likelihood maximisation (equivalent to

loglikihood mamixisation and cross-entropy error minimisation, IRLS update is not required in exam).

• Usage of logistic regression (e.g., suitable for linear,

two-class and multi-class classification). MCQ Linear basis function models.

• Basic idea.
• Be able to compute the new features given the original

features and the basis functions.

• Usage of the model (e.g., suitable for nonlinear

classification). MCQ and written questions

Examination Content and Methods: Chapter 4

5

Content Assessing Method Support vector machines:

• Basic idea of SVM (separation margin, support vectors, slack

variables, and hinge loss).

• Linear/nonlinear, separable/non-separable data patterns.
• Usage of different types of SVM (hard-margin, soft-margin, linear and

kernel SVM). MCQ Kernel trick.

• Basic idea.
• Be able to compute the inner product between two data points given

their original features and the kernel function. MCQ and written questions Data split schemes used in machine learning experiments, and their usage in hyperparameter selection. MCQ Different classification performance measures (confusion matrix, specificity, sensitivity, precision, recall, F1 score). MCQ and written questions.

Examination Content and Methods: Chapter 5

6

Content Assessing Method Single neuron model (adder and activation). MCQ Perceptron algorithm:

• Rules for updating (training) model parameters.
• Usage of the algorithm (linear, two-class classification).

MCQ Multilayer perceptron (feedforward artificial neural network):

• Architecture (input, hidden and output layers)
• Be able to compute the number of neural network parameters to be

trained, given layer number and the neuron number in each layer.

• Basic idea of backpropagation.
• Usage of the method (e.g., suitable for processing nonlinear data

patterns, regression, two-class and multi-class classification). MCQ Deep learning (many hidden layers). MCQ