When we build a model of deep learning, we always use a convolutional layer followed by a pooling layer and several fully-connected layers. It is necessary to know how many parameters in our model as well as the output shape of each layer. …

Before we begin, I want to share anaconda with you. If you are familiar with it, please skip this part. If you need to run different demos on your computer, it is necessary to set up different virtual environments. …

This article will summarize some strategies for machine learning projects. Firstly, we will illustrate the reasons why we need strategies for machine learning. Secondly, we will give you some insights into directions to improve system performance according to its variance and bias. Thirdly, we will go through error analysis which…

We will cover basic ideas of least squares, weighted least squares. Meanwhile, we will discuss the relationship between Recursive Least Squares and Kalman Filters and how Kalman Filters can be used in Sensor Fusion. …

**Introduction**

In this article, we will discuss three methods of vehicle lateral control: Pure pursuit, Stanley, and MPC combined with the result of a project of controlling the vehicle to follow a race track. …

**Why we need Laplace Transform?**

Laplace transform is used to transfer differential equations to algebraic equations, which can then be solved by the formal rules of the **algebra. **Let’s see a simple example first.

As we know, the dynamic equation of the mass-spring-damper system is

𝑚𝑥′′+𝑏𝑥′+𝑘𝑥=𝐹, given initial state 𝑥(0)…

2D bicycle model can be expressed as a simplified car model. This is a classic model that does very well at capturing vehicle motion in normal driving conditions.

The bicycle model we’ll develop is called the front wheel steering model, as the front wheel orientation can be controlled relative to…

Data Scientist, working on NLP, deep learning, machine learning, interested in self-driving cars. Linkedin: https://www.linkedin.com/in/dingyan89/