A beginner's guide to regularization in machine learning.
In this article, we will go through what regularization is, why do we need it, and what are different types of commonly used regularization in machine learning models.
Why regularization?
Regularization is often used as a solution to the overfitting problem in Machine Learning. Common causes for overfitting are
- When the model is complex enough that it starts modeling the noise in the training data.
- When the training data is relatively small and is an insufficient representation of the underlying distribution that it is sampled from, the model fails to learn a generalizable mapping.
A visual walkthrough of the ensemble methods in machine learning with a cheatsheet
Background
Let's say you moved to a new place and want to dine out. How do you find a good place?
Solution 1: Find a food critic who is really good at his/her work and see if he/she has any recommendations for the restaurants in your area
Solution 2: Use Google and randomly look at one user's review for a couple of restaurants.
Solution 3: Use Google and look at multiple users' reviews for a couple of restaurants and average their ratings.
Let us analyze each of the…
LaTeX is the defacto standard in the engineering and science communities when it comes to writing a thesis, report, or research paper, etc. LaTeX provides various features that make it a better candidate as compared to other document-processing tools such as MS Word or LibreOffice. Some of its key features are
- The document looks nice — Apart from all the other advantages of LaTeX, in my opinion, the final document generated by LaTeX looks really nice, properly organized, and better formatted as compared to other document-processing tools.
- No weird accidental formatting problems — In MS Word, you change the placement…
Updates:
Dec 25, 2020: Added Ensemble Methods
A couple of years ago I started applying for internships in the area of Machine Learning and ML system design. I had been studying and actively researching in the area of ML for a few years then. I was familiar with most of the basic topics. But when I started interviewing, I realized that though I had a general understanding of the topics, I required a quick go-through before I can answer it perfectly.
So I decided to refresh my concepts. I realized that before every interview, I was required to go through…
Convert face dataset to masked dataset
Jump to code: https://github.com/aqeelanwar/MaskTheFace
What is MaskTheFace?
MaskTheFace is a computer vision-based script to mask faces in images. It uses a dlib based face landmarks detector to identify the face tilt and six key features of the face necessary for applying the mask. Based on the face tilt, the corresponding mask template is selected from the library of the mask. The template mask is then transformed based on the six key features to fit perfectly on the face. The complete block diagram can be seen below. MaskTheFace provides several masks to select from. It is difficult to collect mask datasets under various conditions…
Analyze your WhatsApp chat in the form of interesting graphs
A couple of weeks ago my wife and I started looking at our Whatsapp chat over the last year. There were too many messages and we simply couldn’t go over all of them. I have been using Python for over 3 years now and thought of creating a very simple analyzer to provide me with some useful insights into our WhatsApp chat. The resulting graphs were pretty interesting.
In this article, I will go through the GitHub repository I created for analyzing WhatsApp chat.
AnalyzeTheChat Online Demo:
To check out the online easy-to-use…
Python code for maintaining the Github clones and views statistics for more than 14 days.
GitHub is a great platform for helping developers to store and manage their code. Currently, GitHub only provides statistics for the last 14 days. These statistics include the number of views, unique views, clones, and unique clones. As a developer, I find it a little unresting not to be able to see the lifelong statistics of my GitHub repositories. These lifelong stats will help developers know the importance of their repositories. Based on the traffic, developers can give more attention to certain repositories. Also, sometimes developers might want to display these stats on their website.
A visualization of the basic elements of a Convolutional Neural Network
Visualization is a great tool in understanding rich concepts, especially for beginners in the area. In this article, we will go through the basic elements of a convolutional neural network using visual aids. The article begins with providing a template (visually) for a basic CNN with different building blocks and then discusses the most commonly used elements for each of the building blocks.
Basic CNN Template:
A basic CNN consists of three kinds of layers. Input, hidden, and output as shown below. The data gets into the CNN through the input layer and passes through various hidden layers before getting to the output…
Python platform for Drones in 3D environments
Jump to code: PEDRA GitHub Repository
What is PEDRA?
PEDRA is a programmable engine for Drone Reinforcement Learning (RL) applications. The engine is developed in Python and is module-wise programmable. PEDRA is targeted mainly at goal-oriented RL problems for drones, but can also be extended to other problems such as SLAM, etc. The engine interfaces with the Unreal gaming engine using AirSim to create the complete platform. The figure below shows the complete block diagram of the engine. Unreal Engine is used to create 3D realistic environments for the drones to be trained in. Different levels of details can be added to make…
Note: Idea credits Landing AI
Social-distancing is an important way to slow down the spread of infectious diseases. People are asked to limit their interactions with each other, reducing the chances of the disease being spread with physical or close contact.
In the past decade, AI/Deep Learning has shown promising results in several daily life problems. Various daily life tasks have been automated with the help of AI. In this article, we will go through in detail how can one use python combined with deep learning and computer vision to monitor social distancing. …
