Jingbiao's Blog

「Hinc lucem et pocula sacra」

A night of snow in Cambridge

Parkers Pieces, Cambridge Trumpington Street, Cambridge Peterhouse, Cambridge

Posted by Jingbiao on December 12, 2022, Less than 1 minute to read

4F8 Revisions

Image processing and coding

Frequency responses for image processing Typical questions: What is the effect of windowing on the frequency response of a filter? Directly taking the inverse Fourier Transform for ideal freque...

Posted by Jingbiao on April 11, 2022, 2 minutes to read

4F14 Revisions

Computer systems

ISA Load-store instruction set architecture It is an example of GPR (General Purpose Register) architecture. The operands for the arithmetic and logic operation must be registers not memory addres...

Posted by Jingbiao on April 11, 2022, 7 minutes to read

4F12 Revisions

Computer visions

Question 1 Image structures Implementing Gaussian/Low-Pass Filters Fourier transform of the Gaussian is a low pass filter, with the frequency cut-off at $1/\sigma$ Why smoothing is necessary: ...

Posted by Jingbiao on April 10, 2022, 3 minutes to read

C++ thread dynamic link issue

For multithreading concurrent program in C++, for example: 1 2 3 4 5 6 7 8 9 10 #include <iostream> #include <thread> void thread_init() { std::cout<<"This statement is executed ...

Posted by Jingbiao on February 28, 2022, Less than 1 minute to read

Cross entropy and KL divergence (relative entropy)

\( \require{amstext} \require{amsmath} \require{amssymb} \require{amsfonts} \newcommand{\eg}{\textit{e}.\textit{g}.} \newcommand{\xb}{\mathbf{x}} \newcommand{\yb}{\mathbf{y}} \newcommand{\xbtn}{\ti...

Posted by Jingbiao on January 10, 2022, 1 minute to read

Gaussian Process with GPML toolbox

Statistical machine learning

\( \require{amstext} \require{amsmath} \require{amssymb} \require{amsfonts} \) Function initialization 1 2 3 meanfunc = @meanZero; % zero mean function covfunc = @covSEiso; % Squared E...

Posted by Jingbiao on October 25, 2021, 4 minutes to read

Edge Detections implementation details

Computer visions

1D Edge Detection and the optimizations Simple method: Computing gradient However, with high frequency noises, the gradient could be even more noisier Therefore, Gaussian Smoothing is applie...

Posted by Jingbiao on October 10, 2021, 1 minute to read

ROC Curves and Precision-Recall Curves

Summary ROC Curves summarize the trade-off between the true positive rate and false positve rate for a predictive model using different probability thresholds. Precision-Recall cu...

Posted by Jingbiao on August 22, 2021, 3 minutes to read

Threshold Moving - Finding optimal threshold for classification

Introduction Balanced class A class label is being predicted within a classification task. Most of the time, a threshold of 0.5 is used. Larger than 0.5 for one class (1), smaller than 0.5 for ano...

Posted by Jingbiao on August 22, 2021, 1 minute to read

FEATURED TAGS
Tripos Revision Deep Learning Machine Learning Pytorch Photography Cambridge Communication Python Data Science Multimodal
ABOUT ME

Third year PhD at University of Cambridge.

FRIENDS