DTRANSPOSED data science, AI, technology

Home | DTRANSPOSED

Project - Reinforcement Learning with Unity 3D: G.E.A.R

Over the course of the last several months I was working on a fantastic project organized by the Chair for Computer Aided Medical Procedures & Augmented Reality. As a result, together with a team of students, we have developed a prototype of an autonomous, intelligent agent for garbage collection. The idea has been born during a workshop org... Read more

The best of GAN papers in the year 2018 part 2

The cover image by courtesy of Juli Odomo. As a follow-up to my previous post, where I discussed three major contributions to GANs (Generative Adversarial Networks) domain, I am happy to present another three interesting research papers from 2018. Once again, the order is purely random and the choice very subjective. Large Scale GAN Traini... Read more

The best of GAN papers in the year 2018

This year I had a great pleasure to be involved in a research project, which required me to get familiar with a substantial number of publications from the domain of deep learning for computer vision. It allowed me to take a deep dive into the field and I was amazed by the progress done in the last 2-3 years. It is truly exciting and motivating ... Read more

Practical tutorial- LSTM neural network: A closer look under the hood

Since I have learned about long short-term memory (LSTM) networks, I have always wanted to apply those algorithms in practice. Recently I had a chance to work on a project which requires deeper understanding of the mathematical foundations behind LSTM models. I have been investigating how LSTMs are implemented in the source code of Keras library... Read more

Practical tutorial- Robot localization using Hidden Markov Models

In year 2003 the team of scientists from the Carnegie Mellon university has created a mobile robot called Groundhog, which could explore and create the map of an abandoned coal mine. The rover explored tunnels, which were too toxic for people to enter and where oxygen levels were too low for humans to remain concious. The task was not easy: navi... Read more