Rico's Nerd Cluster

「离开世界之前 一切都是过程」

Deep Learning - Auto Differentiator From Scratch

Auto Diff Is The Dark Magic Of All Dark Magics Of Deep Learning

Introduction Gradients here refer to scalar to matrix gradient. We need to accumulate gradients for mini-batch training. Elementwise Multiplication gradients: A * B = C del C / del A_ij...

Deep Learning - Gradient Checking

First Step To Debugging A Neural Net

How To Do Gradient Checking In calculus, we all learned that a derivative is defined as: \[\begin{gather*} f'(\theta) = \frac{f(\theta + \epsilon) - f(\theta)}{\epsilon} \end{gather*}\] ...

Deep Learning - Introduction

Why Do We Even Need Deep Neuralnets? Data Partition, ML Ops, Data Normalization

Why Do We Need Deep Learning Any bounded continuous function can be approximated by an arbitrarily large single layer. W hy? The idea is roughly that the linear combinations of activation function...

Computer Vision - Pinhole Camera Model

This Blog Shows How A Small Magic Peek Hole Captures The World

Introduction Camera is intriguing. There have been many different types with different types of lenses (such as fisheye, wide angle Lens). However, the most original (and the simplest) form of cam...

Computer Vision - Random Tree

Random Tree

Introduction Simple Example: Predicting Lottery Purchase with a Decision Tree Imagine we have two pieces of information about a person: Age Income The task is: we want to predict whether ...

Robotics - [Motion Planning 1] Overview And A star Variants

A Star

The “old school” path planning pipeline is: 1 Path Planning -> Trajectory Optimization A Star Setup: Maintain a priority_queue to store all nodes to expand The priority queue i...

Computer Vision - Image Downsampling

Bicubic, Bilinear, Nearest Neighbor Interpolation, Ringing Effect

Introduction What is image downsampling?: Image Downsampling is to reduce spatial resolution and make an image smaller. Why performing interpolation during downsampling?: image downsampling essen...

Computer Vision - ORB Features And Matching

This Blog Shows The Theory and Implementation From Scratch of ORB Features

Intro In SLAM and Computer Vision, distinguishing the same points across multiple camera views is necessary for visual odometry. These “distinguishable points” are called features. In general, we ...

Computer Vision - Harris Corner Detector

Do Not Cut Corners on Corner Detector - It Will See It

Basic Idea When a specified window truly has a corner, if we shift a window (region of interest) along any direction (+/- x or y direction) slightly by small displacements, $u$, $v$, we could expe...

Computer Vision - Heuristic Algorithms

K Means

Introduction In mathematical optimization and computer science, heuristic is a technique designed for problem solving more quickly when classic methods are too slow for finding an exact or approxi...