Skip to main content

Posts

Generative Adversarial Network
·753 words·4 mins
A neural network is like a highly sophisticated, multi-layered calculator that learns from data. It consists of numerous “neurons” (tiny calculators) connected in layers, with each layer performing a unique function to help the network make predictions or decisions.
Variational-Auto-Encoder
·729 words·4 mins
The beauty of VAEs lies in their ability to generate new samples by randomly sampling vectors from this known region and then passing them through the generator part of our model.
Auto-Encoder
·545 words·3 mins
An autoencoder begins its journey by compressing input data into a lower dimension. It then endeavors to reconstruct the original input from this compressed representation.
Delaunay Triangulation
·399 words·2 mins
Delaunay triangulation is a process that takes a set of points in n-dimensional space as input and returns a network of triangles connecting these points. The resulting structure is called a triangulation or mesh.
Paltering
·618 words·3 mins
Paltering reminds us that even truthful statements can be used to mislead. Understanding the context and limitations of facts, and the role of scientific method in informing but not dictating actions, is essential.
Done Manifesto
·548 words·3 mins
In today’s fast-paced world, getting things done is crucial. The Done manifesto is all about embracing this mindset and applying it to your work.
Weighted Voronoi Stippling
·793 words·4 mins
Stippling, a timeless artistic technique, traces its origins back through the annals of art history, where it emerged as a method of creating texture, depth, and form through the precise placement of dots.
Hidden Markov Models
·530 words·3 mins
Hidden Markov Models (HMMs) are statistical models used for sequential data analysis, where underlying states are inferred from observed data. Employed in speech recognition, bioinformatics, and more.
Voronoi Diagram
·1043 words·5 mins
Voronoi diagrams, also known as Dirichlet tessellation or Thiessen polygons, are everywhere in nature. You’ve likely encountered them thousands of times, but perhaps didn’t know what they were called.
Less is More Paper Review
·467 words·3 mins
Less is More: Parameter-Free Text Classification with Gzip offers a novel text classification method using gzip compression, eliminating manual parameter tuning.