It is a prerequisite homework for one wants to enroll in this class. Problems relate to privileged instructions, synchronization — thread-safe coding , virtual memory — Translation Lookaside Buffer (TLB), and file system — number of disk reads needed for different file access operations.
Month: February 2021
Latent Variable Final Project
In this project, we want to do some research on restaurant rating system with temporal dynamics. For the experiment dataset, we directly adapt Yelp Competition Dataset for restaurants. After some analysis, we find out there is a quite significant pattern for both restaurant ratings and user ratings over months every year. At the end, we
Latent Variable Homework 4
There are three parts in this homework. Firstly, I work on Markov Random Field and derive the update rules with evidence lower bound (ELBO). Secondly, I use the conclusion from previous derivations and implement Gibbs Sampling and Mean Field Algorithm, both of who take a noisy picture as input and output a denoised picture. Lastly,
Latent Variable Homework 3
In the beginning of this homework, I work on some basic properties of Gaussian variables, including calculating the expectation and convolution of a mixture of `K` Gaussian variables. Later, I am asked to model a problem in terms of PGM and figure out its update. rules. Details of training stage and testing stage are also
Latent Variable Homework 2
This homework is about Metropolis-Hastings, Gibbs Sampling, derivation of update rules, modeling a given problem in terms of Probabilistic Graphical Model (PGM), and practically implementing a program to calculate the update step-by-step. Codes are included in the report.
Latent Variable Homework 1
In the first homework, I am given some problems related to basic probabilities and machine learning, including conditional independent, Bayesian rules, optimization, and practice of deriving the formula of exponential family.
Data Mining and Analysis All Homework
All the homework are about using the Spark to do data analysis. At the end of the quarter, there is a final project, which requires all students to analyze some real data and present the report in iPython.
Computer Vision III Quarter Project
In this quarter project, we are interested in a paper that has not been accepted by conference but available on ArXiv: Vinet: Visual-inertial odometry as a sequence-to-sequence learning problem. Its goal is to achieve better visual-inertial odometry given sequential visions from two camera. In terms of implementation, we need to embed some TensorFlow codes in
Recommendation System and Web Mining Assignment 2
It is an open project for students. After some research, my teammates and I decide to work on a house price prediction task, whose target price is either “low”, “medium”, or “high”. Beside using the basic features that are available intuitively, we spend lots of time in visualizing geographical features with given longitude and latitude.
Continue Reading “Recommendation System and Web Mining Assignment 2”
Recommendation System and Web Mining Assignment 1
This assignment is an extended competition from Hw3. I basically need to use some more complicated model to further improve my model performance. For both helpfulness and rating prediction tasks, I decide to use Matrix Factorization (MF) model with Alternating Least Square (ALS) learning approach. Initially, I use only a predicator and biased term for
Continue Reading “Recommendation System and Web Mining Assignment 1”
Recent Comments