MSc: Advanced Machine Learning

Advanced Machine Learning

• Course name: Advanced Machine Learning
• Code discipline: DS-02
• Subject area:

Short Description

This course covers the following concepts: Advanced topics in machine learning; To develop research interest in the theory and application of machine learning.

Course Topics

Course Sections and Topics

Section	Topics within the section
Neural Networks	Neural Network Architectures Recurrent Neural Networks LSTM and Attention
Graphical Models and Evolutionary Computation	Hidden Markov Model Decoding and inferencing in graphical models Evolutionary Computation - Genetic Algorithm
Collaborative Filtering and Generative Models	Collaborative Filtering Simple GAN Conditional GAN Time-series prediction
Reinforcement Learning	Value-based Reinforcement Learning Policy-based Reinforcement Learning Q-Learning Policy Gradients Deep Q Network (DQN)

Intended Learning Outcomes (ILOs)

What is the main purpose of this course?

This course is designed for graduate students to provide comprehensive and advance topics in machine learning. Student will learn to implement the machine learning models in Python programming environment from data science prospective. In this course, we will cover Neural Network Architectures (CNN, LSTM, Attention, RNN), Regularization, Genetic algorithm, Graphical Models (HMM), Generative models, Reinforcement learning, Collaborative filtering and recent trends in machine learning. The end of the day they will able to apply machine learning algorithms to solve real-world problems.

ILOs defined at three levels

Level 1: What concepts should a student know/remember/explain?

By the end of the course, the students should be able to ...

• Understanding of in depth details about the machine learning models
• Solve the problem in hand by apply machine learning models
• Ability to analyze the models capacity and performances.

Level 2: What basic practical skills should a student be able to perform?

By the end of the course, the students should be able to ...

• Suitability of different machine learning models in different scenarios
• Ability to choose the right model for the given problem

Level 3: What complex comprehensive skills should a student be able to apply in real-life scenarios?

By the end of the course, the students should be able to ...

• Hands on experience to implement different models to know inside behavior
• Sufficient exposure to train and deploy model for the given task
• Fine tune the deployed model in the real-world settings

Grading

Course grading range

Grade	Range	Description of performance
A. Excellent	90-100	-
B. Good	75-89	-
C. Satisfactory	60-74	-
D. Poor	0-59	-

Course activities and grading breakdown

Activity Type	Percentage of the overall course grade
Labs/seminar classes	20
Interim performance assessment	50
Exams	30

Resources, literature and reference materials

Open access resources

• Handouts supplied by the instructor
• Materials from the interment and research papers shared by instructor

Teaching Methodology: Methods, techniques, & activities

Activities and Teaching Methods

Activities within each section

Learning Activities	Section 1	Section 2	Section 3	Section 4
Development of individual parts of software product code	1	1	1	1
Homework and group projects	1	1	1	1
Midterm evaluation	1	1	1	1
Testing (written or computer based)	1	1	1	1
Discussions	1	1	1	1

Formative Assessment and Course Activities

Ongoing performance assessment

Section 1

Activity Type	Content	Is Graded?
Question	What is the role of activation function in artificial neural network?	1
Question	How Recurrent neural network can efficiently utilize the sequential information?	1
Question	How you will evaluate the models that it learns the concept correctly?	1
Question	How you distinguish different neural networks?	1
Question	Implementation of neural networks for classification and regression problems	0
Question	Implement neural networks of natural language processing task	0
Question	Fine tune the neural networks for given problem	0
Question	Find the optimal hyper-parameters to converge the neural network	0

Section 2

Activity Type	Content	Is Graded?
Question	Calculate the probabilities for making decisions	1
Question	Draw the graphical models for given problem	1
Question	Perform the classification task through graphical models	1
Question	Comparison of the models and gold standard test	1
Question	Implement graphical models	0
Question	Perform decoding task	0
Question	Implement inferencing task for the given problem	0
Question	Calculate the performance measures	0
Question	Analyze the model performance.	0

Section 3

Activity Type	Content	Is Graded?
Question	how to find the equilibrium point in GANs?	1
Question	How you can define discriminator and generator?	1
Question	How you can make suitable setting to train the model correctly?	1
Question	How you will evaluate your model?	1
Question	What are the effects of different loss functions?	1
Question	Implement GAN for given task	0
Question	Implement conditional GAN	0
Question	Analysis of different loss functions	0
Question	Experiments to look-inside for network convergence	0

Section 4

Activity Type	Content	Is Graded?
Question	What are the different kinds of Reinforcement Learning?	1
Question	What is the relationship between the agent and state?	1
Question	How you define fully and partially observed states?	1
Question	Explain Markov decision process in fully observed situations	1
Question	Implement Q learning algorithm	0
Question	Analyze the performance of DQN	0
Question	Understand the loss functions and network architecture details	0
Question	Apply reinforcement learning to a given task	0

Final assessment

Section 1

1. Calculate the parameters for the given dataset
2. Analyze the problem and choose the correct neural network for the given problem
3. Explanation of the model selection and designed architecture
4. Different learning rates and initialization
5. Batch processing and GPU consideration

Section 2

1. Design and analyze the graphical models
2. Dry run the model to make decisions for classification tasks
3. Calculate the performance measures
4. Perform the analysis over the given dataset

Section 3

1. Design and define the generative models for the given task
2. What are the possible solutions to make the training fast?
3. How you can initialize the data distribution and its impact.
4. What are the possible solutions if discriminator is two strong?

Section 4

1. Calculate the next move of the agent in fully observed state
2. Explain the model outcome in reinforcement learning scenarios
3. What kind of tasks we can solve through reinforcement learning models?
4. Calculate the value of an agent for the next move

The retake exam

Section 1

Section 2

Section 3

Section 4