Representing concepts efficiently

This week’s post is about “Semantic Folding Theory and its Application in Semantic Fingerprinting” by Webber . The basic ideas were also discussed in this Braininspired podcast, and also presented and recorded at the HVB Forum in Munich. You don’t need any particular prior knowledge to understand this post, but if you are generally interested …

Predicting the future with world models

This week’s article is “World Models” by Ha and Schmidhuber . You can find a fancy interactive version of the article here. To understand this post, you need to have a basic understanding of neural networks, recurrent neural networks / LSTMs and reinforcement learning. In my own words Let’s say you want to train a …

Conditional neural processes

This week’s article is “Conditional Neural Processes” by Garnelo et al. . To understand this post, you need to have a basic understanding of neural networks and Gaussian processes. In my own words A neural process (NP) is a novel framework for regression and classification tasks that combines the strengths of neural networks (NNs) and …

Gaussian processes

This week I discuss a lecture by David MacKay on “Gaussian Process Basics”. Unfortunately, the video on that website requires Flash support, which is obsolete and I am not going to install it. Luckily, someone seems to have uploaded a recording to YouTube. To understand this post, you need to have a basic understanding of …

Reinforcement learning and Rubik’s Cube

This week’s article is “Solving the Rubik’s Cube Without Human Knowledge” by McAleer, Agostinelli, Shmakov, and Baldi , which was submitted to NeurIPS 2018. To understand this article, you need to have a basic understanding of neural networks and be familiar with reinforcement learning. In my own words The Rubik’s Cube is a 3-dimensional combination …