-
February 7, 2024
I Completed The David Goggins Challenge And Asked My Garmin How I Did
The challenge is simple: run 4 miles (6.5 kilometers) every 4 hours, across 48 hours. When you do the math, the challenge is the equivalent of running almost two marathons within two days.
-
November 2, 2023
A Video Game that Pays: Lessons Learned from Working Remotely
Remote work is a video game that pays. However, on a serious note, remote work has its own set of pros and cons, that I want to share in this blog post.
-
August 6, 2022
Deep Dive into NeRF (Neural Radiance Fields)
Set out to finally understand how this cool invention called NeRF (Neural Radiance Fields). In this post, I am documenting my analysis of the algorithm. I simply run the code through my debugger, analyze what is going on step-by-step, and cross-reference my understanding with the original paper. And plotting - a lot of plotting to visualize concepts; we humans are visual beasts after all.
-
December 24, 2021
Learning by Doing - the DeFi Quest (Part 2 out of 2)
The DeFi quest continued.
-
December 11, 2021
Learning by Doing - the DeFi Quest (Part 1 out of 2)
I find Decentralised Finance (DeFi) truly fascinating because it promises to solve so many problems of the modern financial world. It gives hope, that the future will be much less dystopian than we think. The goal of this series of blog posts is to document my first, applied steps in the world of DeFi.
-
May 1, 2021
So You Want to Study Computer Science (in Europe)?
When I was thinking about the choice of my Master's degree, I remember asking many people for advice. Fast forward to today, I have decided to share some of my experience in this blog post.
-
April 5, 2021
Mixed Martial Maths - Simple Reasoning Tools For Complex Phenomena
The goal of this article is to present several reasoning tools, which will allow you to answer Fermi questions, harness complexity and make you less wrong on the daily basis.
-
January 3, 2021
Notes - Prisoners of Geography (Tim Marshall)
Over the Christmas holidays I finally managed to finish one of my 2020 lockdown projects. After reading the (excellent) book by Tim Marshall, I summarized every chapter in the book.
-
October 21, 2020
Robotic Assembly Using Deep Reinforcement Learning
The goal of this tutorial is to show how you can apply Deep RL to solve your own robotic challenge. By the time you finish the tutorial, you will understand how to create an end-to-end pipeline for training the robot in the simulation.
-
October 12, 2020
Research Paper Summary - The AI Economist: Improving Equality and Productivity with AI-Driven Tax Policies
The AI Economist, is a study on how to improve economic design through the AI-driven simulation. The goal of the study is to optimize productivity and social equality of the economy.
-
April 13, 2020
Option Pricing - Introduction, Example and Implementation
I introduce the concept of financial options, show their application in financial engineering and implement two option pricing models - Black-Scholes and Binomial Option Pricing models.
-
January 3, 2020
Tutorial - Sequential Bayesian Learning - Linear Regression
Step-by-step tutorial on sequential Bayesian learning, along with the accompanying code. I use linear regression using maximum likelihood estimation to obtain a probabilistic estimate of the parameters of the linear model.
-
August 12, 2019
Tutorial - Visual Attention for Action Recognition
Visual attention for action recognition: short overview of the history, discussion of the neural network architectures together with the implementation details and results.
-
May 16, 2019
Understanding AlphaGo Zero [1/3]: Upper Confidence Bound, Monte Carlo Search Trees and Upper Confidence Bound for Search Trees
I discuss crucial concepts required for the deeper understanding of AlphaGo: Upper Confidence Bound (UCB), Monte Carlo Search Trees (MCST) and Upper Confidence Bound for Search Trees (UCT).
-
March 10, 2019
Project - Reinforcement Learning with Unity 3D: G.E.A.R
We have developed a prototype of an autonomous, intelligent agent for garbage collection. The agent navigates in the environment (a mock-up of German Oktoberfest tent) using camera RBG-D input."
-
January 25, 2019
The best of GAN papers in the year 2018 (part 2)
As a follow-up to my previous post, where I discussed my favourite GANs publications, I am happy to present the second batch of interesting research papers from 2018.
-
December 31, 2018
The best of GAN papers in the year 2018
A quick overview of the most interesting publications from 2018 regarding GANs. The list is highly subjective - I have chosen research papers which were not only state-of-the-art, but also cool and highly enjoyable.
-
May 19, 2018
Tutorial- LSTM neural network: A closer look under the hood
The goal of this tutorial is to perform a forward pass through LSTM network using two methods. The first approach: use a model from Keras library. The second approach: implement the forward pass using only numpy library.
-
April 1, 2018
Tutorial- Robot localization using Hidden Markov Models
The goal of this tutorial is to show how we can use Hidden Markov Models to tackle the problem of robotic localization. To illustrate the method, I will use the scenario of a mobile robot operating in a warehouse.
-
December 27, 2017
Bayesian thinking- What can we learn about reasoning from the machines?
Bayesian reasoning may be one of the most important mathematical tools we could apply in real life. It is a powerful means to test and enhance our thinking so that we can overcome common fallacies of reasoning.