Classical ML and Deep Learning
Formulating and Implementing the t-SNE Algorithm From Scratch
The most extensive visual guide to never forget how t-SNE works.
Avi Chawla
410 posts published
Classical ML and Deep Learning
Bayesian Optimization for Hyperparameter Tuning
The caveats of grid search and random search and how Bayesian optimization addresses them.
Classical ML and Deep Learning
Formulating and Implementing XGBoost From Scratch
An extensive visual guide to never forget how XGBoost works.
Classical ML and Deep Learning
Formulating the Principal Component Analysis (PCA) Algorithm From Scratch
Approaching PCA as an optimization problem.
Classical ML and Deep Learning
You Are Probably Building Inconsistent Classification Models Without Even Realizing
The limitations of always using cross-entropy loss in ordinal datasets.
Classical ML and Deep Learning
Why R-squared is a Flawed Regression Metric?
The lesser-known limitations of the R-squared metric.
Classical ML and Deep Learning
Generalized Linear Models (GLMs): The Supercharged Linear Regression
The limitations of linear regression and how GLMs solve them.
Classical ML and Deep Learning
Why Sklearn’s Logistic Regression Has no Learning Rate Hyperparameter?
What are we missing here?
Classical ML and Deep Learning
Why Do We Use log-loss To Train Logistic Regression?
The origin of log-loss.
Classical ML and Deep Learning
Why Do We Use Sigmoid in Logistic Regression?
The origin of the Sigmoid function and a guide on modeling classification datasets.
Classical ML and Deep Learning
The Probabilistic Origin of Regularization
Where did the regularization term come from?
Classical ML and Deep Learning
Where Did The Assumptions of Linear Regression Originate From?
The most extensive and in-depth guide to linear regression.
Classical ML and Deep Learning
Why is ReLU a Non-Linear Activation Function?
The most intuitive guide to ReLU activation function ever.
Machine Learning
A Reliable and Efficient Technique To Measure Feature Importance
Measure feature importance through chaos.
Plotting
AutoProfiler: Automatically Profile Your DataFrame As You Work
...without writing any redundant code.
Plotting
A Little Bit Of Extra Effort Can Hugely Transform Your Storytelling Skills
Always keep the viewer in mind.
Python
A Nasty Hidden Feature of Python That Many Programmers Aren't Aware Of
...and counterintuitive when you discover it.
Plotting
Interactively Visualise A Decision Tree With A Sankey Diagram
and prevent overfitting.
Plotting
Use Histograms With Caution. They Are Highly Misleading!
Instead, try these alternatives.
Plotting
Three Simple Ways To (Instantly) Make Your Scatter Plots Clutter Free
Towards better data visualisation.
Lesser Known
A (Highly) Important Point to Consider Before You Use KMeans Next Time
Estimating the success rate of KMeans.
Run-Time Optimization
Why You Should Avoid Appending Rows To A DataFrame
...and what happens if you do.
Plotting
Matplotlib Has Numerous Hidden Gems. Here's One of Them.
A cool trick to improve Matplotlib plots.
Python
A Counterintuitive Thing About Python Dictionaries
...which many python programmers get confused with.
Python
Probably The Fastest Way To Execute Your Python Code
So the best way to speedup python is by not using python?
Pandas
Are You Sure You Are Using The Correct Pandas Terminologies?
If not, let's revisit.
Machine Learning
Is Class Imbalance Always A Big Problem To Deal With?
May be not.
Plotting
A Simple Trick That Will Make Heatmaps More Elegant
Embedding the size component to a heatmap.
Machine Learning
A Visual Comparison Between Locality and Density-based Clustering
The biggest limitation of locality-based clustering.
Lesser Known
Why Don't We Call It Logistic Classification Instead?
Start questioning the names of other algorithms too. It will be a fun activity.