Smiley face
  • Evolutionary algorithms
    Oswald Berthold - Quick introduction to evolutionary algorithms
  • Policy Gradient Methods
    Felix Assion - In this post the key concepts behind Policy Gradient Methods will be discussed. Sample topics are the REINFORCE algorithm and the Policy Gradient Theorem. In the end, the learned algorithms will be used to solve the MountainCar environment of the OpenAI Gym.
  • Recurrent Neural Networks - 03 Neural Turing Machine
    Wiebke Günther - This is the third part of a series of blogposts about Recurrent Neural Networks (RNNs). It will cover the topic of Neural Turing Machines (NTM).
  • Recurrent Neural Networks - 02 Long Short-Term Memory
    Wiebke Günther - This is the second part of a series of blogposts about Recurrent Neural Networks (RNNs). It will cover the topic of Long Short-Term Memory (LSTM).
  • Recurrent Neural Networks - 01 General Information
    Wiebke Günther - This series of blogposts will cover a small portion of what there is to know about Recurrent Neural Networks (RNNs). Within this very wide topic it will focus on the special cases of Long Short-Term Memory (LSTM) and Neural Turing Machines.
  • Introduction to Blockchain Technology
    Frank Selensky - This post gives a brief introduction to the blockchain technologies as they are used in cryptocurrencies like bitcoin.
  • Introduction to Reinforcement Learning: Part 3 - Q-learning
    Felix Assion - The famous Q-learning algorithm will be introduced and applied to an easy environment of the OpenAI Gym.
  • Introduction to Tensorflow - 03 Neural Network
    Florens Greßner - While showing how to build to a simple neural network with TensorFlow I want to give the reader a playful handling of namescopes and show how to make sense of your weight evolution with histograms.
  • Introduction to Tensorflow - 02 Tensorboard
    Florens Greßner - While showing how to evaluate derivatives from a TensorFlow computation graph I want to give the reader the basic tool for visualizing a model.
  • Introduction to Tensorflow - 01 Basics
    Florens Greßner - While giving an overview of Python, NumPy and TensorFlow I want to create a basic understanding of TensorFlows graph representation for the reader.
  • Introduction to Reinforcement Learning: Part 2 - Dynamic Programming
    Felix Assion - The different Bellman Equations will be introduced. Afterwards we discuss Value and Policy Iteration and sketch proofs of those dynamic programming algorithms.
  • Introduction to Reinforcement Learning: Part 1 - the Framework
    Felix Assion - We will discuss the mathematical framework for RL problems - namely, Markov Decision Processes. The concept of value functions and action-value functions will be introduced. This series of posts is basically a brief summary of a workshop I held at the startup neurocat.