Course:CPSC522

CPSC 522 Wiki
CPSC 522
Section:
Instructor:	David Poole
Email:	poole@cs.ubc.ca
Office:	109
Office Hours:	after class every day
Class Schedule:
Classroom:	DMP 101
Important Course Pages
	Syllabus
	Lecture Notes
	Assignments
	Course Discussion

Welcome to CPSC 522 Wiki. This is where the participants are writing the textbook. See http://www.cs.ubc.ca/~poole/cs522/2023W1/ for the main web page for the course.

The 2023 Rules

• These rules are editable, so you can change the rules.
• October Assignment describes your assignments for October.
• November Assignment describes your assignment for November.
• December Assignment describes your final assignment.
• Do not plagiarize; give references to all sources. Put quotes in quotes. Taking something from another source and not attributing it clearly, will result in disciplinary action.
• All pages should follow the CPSC522 Template
• Give links, but make sure that the pages are readable (with sentences) without following the links.
• Link to all prerequisite pages (those the page builds on) in the appropriate place in the template. The prerequisite pages should not form a cycle.
• Link to all related pages; it should be easy for someone to determine that a page on a particular topic does not exist.
• The web pages created should all be in the Course:CPSC522 hierarchy, but should not contain "Course:CPSC522" in the visible link. Hint: create a link to the page before the page exists, then you will be asked to create the page,
• If you want to abandon a page that others are relying on (e.g., you are the principal author and they are coauthors) you need to negotiate with them to make sure no one is disadvantaged.
• All pages should be in the Index and the table of contents below.

Guidelines

• Keep each page as simple as possible (but not simpler); if a page starts to get complicated, consider splitting it.
• Write pages for your peers; they should all be written for incoming graduate students, and only assume background knowledge that is common among such students.
• All pages should obey the Syntax Conventions. If there is a design decision that you need to make that may have non-local implications, add it to the conventions.
• It should use formalism and mathematics when (and only when) the formalism make the description clearer. Use the code tags for math, e.g., $P(h\mid e)={\frac {P(h\land e)}{P(e)}}.$ It is worth your while to learn Latex if you don't already know it.
• If there is a simple case, and a more general case, give the simple case first. Making things complicated is easy; keeping them simple is difficult and we should strive for simplicity. Any complication needs to be carefully motivated.
• Use the "discussion" tab

Each Page should contain:

• A clear jargon-free description of what is going on. Keep jargon to a minimum.
• Motivating example(s) and, where appropriate, a simple pedagogical example (which may be different from the motivating examples) that is used to explain what is going on
• An argument of plausibility
• Evidence that it works
• Code and pseudo-code, where appropriate. This code should interact with other related code (e.g., AIFCA Python Distribution) if possible. The code should be as simple as possible to implement the techniques. Consider adding exercises as to what can be improved or made more general or bullet-proof. Use a code block for (pseudo-)code (even multi-line code). You can also use the format in http://wiki.ubc.ca/Course:CPSC_320/Midterm_2_Reference_Sheet#Pseudocode (try both and see which better suits your needs).

Foundations

Please add your page here and in the Index.

• My Test

General

• Artificial General Intelligence (2018)
• Swarm Intelligence (2018)
• M0 Differential Privacy (2022W2)

Control

• Control Theory (2016)
• Hierarchical Control (2016)
• M1 Genetic Algorithms (2022W2)

Probability and Graphical Models

• Probability (2016)
• Graphical Models (2016)
• Bayesian Networks (2016)
• Markov Networks (2016)
• Weighted Model Counting(2019)

Temporal Models

• Markov Chains (2018)
• Hidden Markov Models (2016)
• Kalman filter (2018)
• Dynamic Bayesian Networks (2018)

Inference

• Variable Elimination (2016)
• Markov Chain Monte Carlo (2016)
• Particle Filtering (2016)
• Treatment of Missing Data (2019)
• Bayesian Coresets (2019)
• Variational Inference (2020)

Causality

• Causality (2016)

Representations of Conditional Probability

• Neural Network (2016)
• Recurrent Neural Networks (2018)
• M2 Long Short-Term Memory Networks (2022W2)
• Decision Trees (2018)

Learning

• Learning Probabilistic Models with Complete Data (2018)
• Support Vector Machines (2018)
• Ensemble Learning (2018)
• Principal Component Analysis (PCA) (2020)
• Self-Organizing Maps (2020)
• Progressive Neural Network (2020)
• Conditional GANs for Image-To-Image Translation (2020)
• M3 Normalizing Flows (2022W2)

Natural Language Processing

• Natural Language Processing (2018)
• Probabilistic Context Free Grammars (2018)
• M4 Transformer Models (2022W2)
• Scaling Memory for Transformers (2023W1)

Deep Learning with Graphs

• M5 Graph Neural Networks (2022W2)

Utility and Preferences

• Bounded Rationality (2018)
• Elicitation of Factored Utilities (2019)
• Matrix Factorization For Recommender Systems (2023)

Acting Under Uncertainty

• Decision Networks (2016)
• Markov Decision Process (2016)
• Partially Observable Markov Decision Processes (2020)
• Reinforcement Learning (2016)
• Reinforcement Learning with Function Approximation (2016)
• Game Theory (2016)
• Multi-Agent Systems (2018)
• Stochastic Optimization (2018)
• Value of Information (2019)
• F9 Bayesian Optimization (2022W2)
• M6 Using Causal Graphs with Bayesian Optimization

Logic

• Abduction (2018)
• Knowledge Compilation (2016)
• Predicate Calculus (2016)
• Markov Logic (2018)
• Higher Order Logic (2018)
• Ontology (2019)
• M7 Knowledge Graphs (2022W3)

December 2023 Assignment

• D0: Collaborative Filtering on Movie Lens Dataset
• D1: Alpha Function in Q-Learning
• D2: Gender Classification using Temporal Patterns in Movie Ratings
• D3: Recursive Error Division Validation

November 2023 assignment

• N0: Decision Tree Approach to Decision-Support Systems in Medicine
• N1: Utility Assessment for Decision Support System
• N2: Patient-Centric Decision Support: The Utility Assessment Method
• N3: Rejecting Homogeneous Solutions, Avoiding Medical Labels, and Relational Design

Existing Combinations (2023)

• O0: Probabilistic Models for Single Cell Sequencing
• O1: Matrix Factorization For Recommender Systems
• O2: Scaling Memory for Transformers
• O3: Multi-Attribute Utility

Existing Combinations (2022W2)

• put link here (see other links for format; try looking at the Source editor (the pencil in the menu))
• Pretraining Methods for Graph Neural Networks
• Knowledge-Aware Graph Networks for Commonsense Reasoning
• Variational Recurrent Neural Networks
• Hyperspherical Variational Auto-Encoders
• MDP for Differentially Private Reinforcement Learning
• Diffusion Probabilistic Models
• Is attention explanation?
• Vision Transformers (ViT)
• Bayesian Optimization
• for F9 see under Acting Under Uncertainty
• Neural Architecture Search (2022W2)
• Stable Diffusion: Image to Prompts
• Using SHapley Additive exPlanations for hyperparameter value pruning in Bayesian Optimization
• Concatenating Hyperspherical Distributions in Hyperspherical VAE
• Multinomial Variational Autoencoders for Predicting Gender in MovieLens
• Graph Neural Networks for Roadgraph Encoding

Existing Combinations (2016)

• Recommendation System using Matrix Factorization
• Latent Dirichlet Allocation
• Deep Neural Network and Game of Go
• Problog
• Maximum Entropy Markov Models
• Ontology Search Engine
• Convolutional Neural Networks
• Learning Markov Logic Network Structure
• Decision Support System using Interactive Preference Elicitation
• Predicting Affect of User's Interaction with an Intelligent Tutoring System
• Record Linkage and identity uncertainty
• Robot Scientist
• Density-Based Unsupervised Learning
• Predicting Human Behavior in Normal-Form Games
• Identity Uncertainty
• Generative Adversarial Networks
• Inductive Logic Programming
• User-Adaptive Information Visualization

Existing Combinations (2020)

• Pedestrian localization for Indoor Environments (2020)
• Automation of hypothesis generation and testing in science (2020)
• Prioritized Experience Replay (2020)
• Variational Auto-Encoders (2020)
• Hybrid Recommendation Systems (2020)
• Online Pattern Analysis by Evolving Self-organizing Maps (2020)

Existing Combinations (2018)

Neural Networks

• Financial Forecasting using LSTM Networks (2018)
• Character Level Language Models using LSTM (2018)
• Text Summarization using Machine Learning (2018)
• Password Cracking using Probabilistic Context Free Grammars and Neural Networks (2018)
• CNNs in Image Segmentation(2018)
• Image Classification With Convolutional Neural Networks (2018)
• Image Colourization using Deep Learning(2018)
• Stacked Generative Adversarial Networks (2018)

Reinforcement Learning

• Deep Q-Learning (2018)
• Deep Reinforcement Learning (2018)
• Self-Improving Machines (2018)
• Adaptive Network Routing using Ant Colony Optimization (2018)

Decision-theoretic Planning

• Action Selection for MDPs (2018)
• Rao-Blackwellized Particle Filtering(2018)

Relational Reasoning

• Transfer Learning with Markov Logic (2018)
• Cognitive Robotics (2018)

Applications

• Affect Prediction using Eye Gaze (2018)
• Conflict-Driven Clause Learning for the Boolean Satisfiability Problem (2018)

Existing Combinations (2019)

• Ontology Extraction
• Restricted Boltzmann Machines for Collaborative Filtering
• Minimax Regret Preference Elicitation for Risky Prospects
• Sequential Monte Carlo samplers
• FastSLAM
• Sequential Monte Carlo for Probabilistic Graphical Models

Future combinations (2016)

• Sentiment Analysis: Movie Reviews
• Collaborative Filtering
• List Recommendation
• Inactive Cookie Mapping via Trail Matching
• Improve Recommendation System by Integration
• Identity Uncertainty in a restaurant data-set
• Regularization for Neural Networks
• Spam Detection
• Titanic: Machine Learning from Disaster
• Automatic Classification of Morphological Heart Arrhythmia
• Linking Sentences in Asynchronous Conversations
• Generic Aspect-based Aggregation of Sentiments
• Graph Based Key-corporation Extraction
• Improving the accuracy of Affect Prediction in an Intelligent Tutoring System
• Improving Human Behavior Prediction in Simultaneous-Move Games
• The Automation of Disease Diagnosis
• Analyzing online dating trends with Weka

Future combinations (2018)

• Artificial Intelligence and Economic Theory
• Weak Semantic Map: Simplified Chinese
• Datacenter Traffic as Reinforcement Learning Problem
• A Theoretical Baseline of Recursive Self-improvement
• Text summarization for busy people!!
• An evaluation on selecting and applying Recommendation Methods
• Learning User Preferences of Motion Control
• Experiments with Reinforcement Learning
• A Comparison of LDA and NMF for Topic Modeling on Literary Themes
• Analysis of hierarchical prior for Language modeling
• Better Caching using reinforcement learning
• Evaluating Ant Colony Optimization in a simulation
• SLAM and Sensor Quality
• Text generation with LSTM and Markov Chain
• Topology and Embedding Multi-relational Data

Future combinations (2019)

• Reinforcement Learning with Linear Model of Reward Corruption
• Adversarial Belief Propagation
• Using Subset Information with Matrix Factorization
• Learning Attention via Active Inference
• Regularization as an Alternative to Negative Sampling in KGs

Future combinations (2020)

• M0 Grouped Prioritized Experience Replay (GPER)
• M1 Alternative Classifiers
• M2 Improving Prediction Accuracy of User Cognitive Abilities for User-Adaptive Narrative Visualizations
• M3 Exploring Results of Conditional Generative Adversarial Networks with Self-Organizing Maps

Suggested Unclaimed Pages

Here are some possible topics for pages. This list is not meant to limit your imagination. Some of them might be better split into multiple pages. There are many other possible topics.

When claimed, these pages should be moved from this section to the table of contents above and to the Index of existing pages. To claim a page you have to actually create it and edit it (and have your name on the page, so everyone can see who has claimed it).

• Probability - general semantics with infinitely many variables and/or variables with infinite domains
• Representations of Conditional Distributions
• Recursive Conditioning
• Parity Methods for Probabilistic Inference
• Matrix Factorization
• Utility
• Preference Elicitation
• Mechanism Design
• Logic Programming
• Negation as Failure
• Equality/Identity
• Inductive Logic Programming
• Ontologies
• Continual Learning