Posts
autograd: simple library for automatic gradient calculation in DNNs
Motivation
TinyGPUlang: tutorial on how to implement gpu backend with LLVM
Motivation
QR algorithm: finding eigenvalues
Motivation
A lot of iterative algorithms exist in linear algebra to find eigenvalues of symmetric matrices. QR algorithm addresses the issue of finding eigenvalues of nonsymmetric matrices as well. More accurately this algorithm can find real eigenvalues but complex ones are not treated well.
NNSharp: running pre-trained DNNs
Introduction
I have started a project named NNSharp which aims for creating a C# library to run DNNs on Windows.
Reinforcement Learning: Introduction IV
Introduction
This is the last part of a four parts long series about reinforcement learning. In this part an interesting case study is covered: the replication of the Double DQN algorithm.
Reinforcement Learning: Introduction III
Introduction
This is the third part of a four parts long series about reinforcement learning. In this part the main focus is on solving the Bellman-equation.
Reinforcement Learning: Introduction II
Introduction
This is the second part of a four parts long series about reinforcement learning. In this part the core mathematical concepts are covered: MDP, value-function and Bellmann-equation.
Reinforcement Learning: Introduction I
Introduction
This is the first part of a four parts long series about reinforcement learning (hereafter RL). First, I will introduce the different types of machine learning. Then the focus will shift toward RL. I will explain the most important terms and show some examples. The goal of this part is to become more familiar with the core concepts of RL.
High Performance Computing
Introduction
Moore-law is a well-known, famous prediction which states that the number of transistors per square mm is doubling roughly in every 18 months. This clearly causes the fast development of the available computational power which is the basis of the increasing performance of IT systems. But what will happen after the end of the Moore’s Law?
The meaning of AI in the mirror of the future
Introduction
Nowadays, we hear about AI on a regular base due to its fast development. A huge bunch of novels, films were written in connection with this strange part of technology. Almost all of them grabs some negative sides of AI and paints a threatening picture about human’s future.